Personal model library
Sign in to keep a private model list with tags, notes, filters, hardware guidance, and export controls.
Saved models belong to your private account, so the list is available only after you sign in.
After import, this one-time browser list will be removed.
0 models
Loading your saved models…
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
ollama run gemma4Sign in and add your RAM or GPU for compatibility guidance.
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
ollama run qwen3.6Sign in and add your RAM or GPU for compatibility guidance.
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
ollama run laguna-s-2.1Sign in and add your RAM or GPU for compatibility guidance.
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
ollama run laguna-xs-2.1Sign in and add your RAM or GPU for compatibility guidance.
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
ollama run ornith-1.5Sign in and add your RAM or GPU for compatibility guidance.
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
ollama run qwen3.8Sign in and add your RAM or GPU for compatibility guidance.
Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.
ollama run muse-glimmerSign in and add your RAM or GPU for compatibility guidance.
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
ollama run deepseek-v4-proSign in and add your RAM or GPU for compatibility guidance.
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
ollama run nemotron-3.5-lightningSign in and add your RAM or GPU for compatibility guidance.
DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
ollama run deepseek-v4-flashSign in and add your RAM or GPU for compatibility guidance.
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
ollama run kimi-k3Sign in and add your RAM or GPU for compatibility guidance.
Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
ollama run laguna-xs.2Sign in and add your RAM or GPU for compatibility guidance.
A self-improving family of open-source models for agentic coding
ollama run ornithSign in and add your RAM or GPU for compatibility guidance.
North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
ollama run north-mini-code-1.0Sign in and add your RAM or GPU for compatibility guidance.
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
ollama run glm-5.2Sign in and add your RAM or GPU for compatibility guidance.
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.
ollama run kimi-k2.7-codeSign in and add your RAM or GPU for compatibility guidance.
Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
ollama run granite4.1-guardianSign in and add your RAM or GPU for compatibility guidance.
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
ollama run glm-4.7-flashSign in and add your RAM or GPU for compatibility guidance.
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
ollama run nemotron-3-ultraSign in and add your RAM or GPU for compatibility guidance.
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
ollama run minicpm-v4.5Sign in and add your RAM or GPU for compatibility guidance.
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
ollama run minicpm-v4.6Sign in and add your RAM or GPU for compatibility guidance.
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
ollama run minimax-m3Sign in and add your RAM or GPU for compatibility guidance.
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
ollama run lfm2.5Sign in and add your RAM or GPU for compatibility guidance.
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
ollama run qwen3.5Sign in and add your RAM or GPU for compatibility guidance.
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.
ollama run granite4.1Sign in and add your RAM or GPU for compatibility guidance.
Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.
ollama run mistral-medium-3.5Sign in and add your RAM or GPU for compatibility guidance.
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
ollama run nemotron3Sign in and add your RAM or GPU for compatibility guidance.
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
ollama run kimi-k2.6Sign in and add your RAM or GPU for compatibility guidance.
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
ollama run medgemmaSign in and add your RAM or GPU for compatibility guidance.
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
ollama run medgemma1.5Sign in and add your RAM or GPU for compatibility guidance.
GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
ollama run glm-5.1Sign in and add your RAM or GPU for compatibility guidance.
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
ollama run nemotron-cascade-2Sign in and add your RAM or GPU for compatibility guidance.
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
ollama run minimax-m2.7Sign in and add your RAM or GPU for compatibility guidance.
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
ollama run nemotron-3-nanoSign in and add your RAM or GPU for compatibility guidance.
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
ollama run nemotron-3-superSign in and add your RAM or GPU for compatibility guidance.
LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.
ollama run lfm2Sign in and add your RAM or GPU for compatibility guidance.
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
ollama run qwen3-coder-nextSign in and add your RAM or GPU for compatibility guidance.
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
ollama run glm-ocrSign in and add your RAM or GPU for compatibility guidance.
LFM2.5 is a new family of hybrid models designed for on-device deployment.
ollama run lfm2.5-thinkingSign in and add your RAM or GPU for compatibility guidance.
A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
ollama run translategemmaSign in and add your RAM or GPU for compatibility guidance.
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
ollama run functiongemmaSign in and add your RAM or GPU for compatibility guidance.
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
ollama run olmo-3.1Sign in and add your RAM or GPU for compatibility guidance.
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
ollama run olmo-3Sign in and add your RAM or GPU for compatibility guidance.
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
ollama run devstral-small-2Sign in and add your RAM or GPU for compatibility guidance.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
ollama run ministral-3Sign in and add your RAM or GPU for compatibility guidance.
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
ollama run devstral-2Sign in and add your RAM or GPU for compatibility guidance.
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
ollama run nomic-embed-text-v2-moeSign in and add your RAM or GPU for compatibility guidance.
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
ollama run rnj-1Sign in and add your RAM or GPU for compatibility guidance.
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
ollama run qwen3-nextSign in and add your RAM or GPU for compatibility guidance.
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
ollama run mistral-large-3Sign in and add your RAM or GPU for compatibility guidance.
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
ollama run deepseek-ocrSign in and add your RAM or GPU for compatibility guidance.
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
ollama run cogito-2.1Sign in and add your RAM or GPU for compatibility guidance.
The most powerful vision-language model in the Qwen model family to date.
ollama run qwen3-vlSign in and add your RAM or GPU for compatibility guidance.
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
ollama run granite4Sign in and add your RAM or GPU for compatibility guidance.
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
ollama run gpt-oss-safeguardSign in and add your RAM or GPU for compatibility guidance.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
ollama run qwen3Sign in and add your RAM or GPU for compatibility guidance.
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
ollama run gpt-ossSign in and add your RAM or GPU for compatibility guidance.
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
ollama run deepseek-v3.1Sign in and add your RAM or GPU for compatibility guidance.
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
ollama run qwen3-embeddingSign in and add your RAM or GPU for compatibility guidance.
Alibaba's performant long context models for agentic and coding tasks.
ollama run qwen3-coderSign in and add your RAM or GPU for compatibility guidance.
EmbeddingGemma is a 300M parameter embedding model from Google.
ollama run embeddinggemmaSign in and add your RAM or GPU for compatibility guidance.
The current, most capable model that runs on a single GPU.
ollama run gemma3Sign in and add your RAM or GPU for compatibility guidance.
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
ollama run mistral-nemoSign in and add your RAM or GPU for compatibility guidance.
The 7B model released by Mistral AI, updated to version 0.3.
ollama run mistralSign in and add your RAM or GPU for compatibility guidance.
Devstral: the best open source model for coding agents
ollama run devstralSign in and add your RAM or GPU for compatibility guidance.
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
ollama run deepseek-r1Sign in and add your RAM or GPU for compatibility guidance.
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
ollama run gemma3nSign in and add your RAM or GPU for compatibility guidance.
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
ollama run mistral-small3.2Sign in and add your RAM or GPU for compatibility guidance.
Magistral is a small, efficient reasoning model with 24B parameters.
ollama run magistralSign in and add your RAM or GPU for compatibility guidance.
Meta's latest collection of multimodal models.
ollama run llama4Sign in and add your RAM or GPU for compatibility guidance.
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
ollama run qwen2.5-coderSign in and add your RAM or GPU for compatibility guidance.
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
ollama run qwen2.5vlSign in and add your RAM or GPU for compatibility guidance.
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
ollama run llama3.2-visionSign in and add your RAM or GPU for compatibility guidance.
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
ollama run phi4-reasoningSign in and add your RAM or GPU for compatibility guidance.
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
ollama run phi4-mini-reasoningSign in and add your RAM or GPU for compatibility guidance.
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
ollama run granite3.3Sign in and add your RAM or GPU for compatibility guidance.
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
ollama run deepcoderSign in and add your RAM or GPU for compatibility guidance.
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.
ollama run cogitoSign in and add your RAM or GPU for compatibility guidance.
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
ollama run mistral-small3.1Sign in and add your RAM or GPU for compatibility guidance.
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
ollama run openthinkerSign in and add your RAM or GPU for compatibility guidance.
EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.
ollama run exaone-deepSign in and add your RAM or GPU for compatibility guidance.
QwQ is the reasoning model of the Qwen series.
ollama run qwqSign in and add your RAM or GPU for compatibility guidance.
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
ollama run command-aSign in and add your RAM or GPU for compatibility guidance.
A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.
ollama run command-r7b-arabicSign in and add your RAM or GPU for compatibility guidance.
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
ollama run phi4-miniSign in and add your RAM or GPU for compatibility guidance.
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
ollama run granite3.2-visionSign in and add your RAM or GPU for compatibility guidance.
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
ollama run granite3.2Sign in and add your RAM or GPU for compatibility guidance.
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
ollama run r1-1776Sign in and add your RAM or GPU for compatibility guidance.
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
ollama run deepscalerSign in and add your RAM or GPU for compatibility guidance.
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
ollama run mistral-smallSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
ollama run granite3.1-denseSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
ollama run granite3.1-moeSign in and add your RAM or GPU for compatibility guidance.
The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.
ollama run command-r7bSign in and add your RAM or GPU for compatibility guidance.
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
ollama run deepseek-v3Sign in and add your RAM or GPU for compatibility guidance.
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
ollama run olmo2Sign in and add your RAM or GPU for compatibility guidance.
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
ollama run phi4Sign in and add your RAM or GPU for compatibility guidance.
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
ollama run dolphin3Sign in and add your RAM or GPU for compatibility guidance.
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
ollama run smallthinkerSign in and add your RAM or GPU for compatibility guidance.
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
ollama run tulu3Sign in and add your RAM or GPU for compatibility guidance.
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
ollama run mixtralSign in and add your RAM or GPU for compatibility guidance.
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
ollama run dolphin-mixtralSign in and add your RAM or GPU for compatibility guidance.
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
ollama run nous-hermes2-mixtralSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
ollama run granite-embeddingSign in and add your RAM or GPU for compatibility guidance.
A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
ollama run falcon3Sign in and add your RAM or GPU for compatibility guidance.
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
ollama run hermes3Sign in and add your RAM or GPU for compatibility guidance.
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
ollama run exaone3.5Sign in and add your RAM or GPU for compatibility guidance.
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
ollama run llama3.3Sign in and add your RAM or GPU for compatibility guidance.
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
ollama run snowflake-arctic-embed2Sign in and add your RAM or GPU for compatibility guidance.
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
ollama run marco-o1Sign in and add your RAM or GPU for compatibility guidance.
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
ollama run sailor2Sign in and add your RAM or GPU for compatibility guidance.
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
ollama run llama3.1Sign in and add your RAM or GPU for compatibility guidance.
Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.
ollama run mistral-largeSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
ollama run granite3-guardianSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.
ollama run granite3-denseSign in and add your RAM or GPU for compatibility guidance.
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
ollama run granite3-moeSign in and add your RAM or GPU for compatibility guidance.
OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
ollama run opencoderSign in and add your RAM or GPU for compatibility guidance.
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
ollama run minicpm-vSign in and add your RAM or GPU for compatibility guidance.
Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
ollama run athene-v2Sign in and add your RAM or GPU for compatibility guidance.
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
ollama run smollm2Sign in and add your RAM or GPU for compatibility guidance.
Cohere For AI's language models trained to perform well across 23 different languages.
ollama run aya-expanseSign in and add your RAM or GPU for compatibility guidance.
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
ollama run nemotronSign in and add your RAM or GPU for compatibility guidance.
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
ollama run shieldgemmaSign in and add your RAM or GPU for compatibility guidance.
Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.
ollama run llama-guard3Sign in and add your RAM or GPU for compatibility guidance.
Meta's Llama 3.2 goes small with 1B and 3B models.
ollama run llama3.2Sign in and add your RAM or GPU for compatibility guidance.
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
ollama run qwen2.5Sign in and add your RAM or GPU for compatibility guidance.
Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU
ollama run solar-proSign in and add your RAM or GPU for compatibility guidance.
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
ollama run nemotron-miniSign in and add your RAM or GPU for compatibility guidance.
A state-of-the-art fact-checking model developed by Bespoke Labs.
ollama run bespoke-minicheckSign in and add your RAM or GPU for compatibility guidance.
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
ollama run deepseek-v2.5Sign in and add your RAM or GPU for compatibility guidance.
A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
ollama run reader-lmSign in and add your RAM or GPU for compatibility guidance.
Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.
ollama run yi-coderSign in and add your RAM or GPU for compatibility guidance.
Qwen2 is a new series of large language models from Alibaba group
ollama run qwen2Sign in and add your RAM or GPU for compatibility guidance.
A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
ollama run reflectionSign in and add your RAM or GPU for compatibility guidance.
StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
ollama run starcoder2Sign in and add your RAM or GPU for compatibility guidance.
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
ollama run deepseek-coder-v2Sign in and add your RAM or GPU for compatibility guidance.
A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
ollama run phi3.5Sign in and add your RAM or GPU for compatibility guidance.
Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
ollama run codestralSign in and add your RAM or GPU for compatibility guidance.
A family of open foundation models by IBM for Code Intelligence
ollama run granite-codeSign in and add your RAM or GPU for compatibility guidance.
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
ollama run command-r-plusSign in and add your RAM or GPU for compatibility guidance.
Command R is a Large Language Model optimized for conversational interaction and long context tasks.
ollama run command-rSign in and add your RAM or GPU for compatibility guidance.
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
ollama run qwen2-mathSign in and add your RAM or GPU for compatibility guidance.
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
ollama run smollmSign in and add your RAM or GPU for compatibility guidance.
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
ollama run internlm2Sign in and add your RAM or GPU for compatibility guidance.
BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
ollama run bge-m3Sign in and add your RAM or GPU for compatibility guidance.
Sentence-transformers model that can be used for tasks like clustering or semantic search.
ollama run paraphrase-multilingualSign in and add your RAM or GPU for compatibility guidance.
Embedding model from BAAI mapping texts to vectors.
ollama run bge-largeSign in and add your RAM or GPU for compatibility guidance.
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
ollama run gemma2Sign in and add your RAM or GPU for compatibility guidance.
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
ollama run phi3Sign in and add your RAM or GPU for compatibility guidance.
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
ollama run llama3-groq-tool-useSign in and add your RAM or GPU for compatibility guidance.
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
ollama run nuextractSign in and add your RAM or GPU for compatibility guidance.
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.
ollama run codegemmaSign in and add your RAM or GPU for compatibility guidance.
A large language model that can use text prompts to generate and discuss code.
ollama run codellamaSign in and add your RAM or GPU for compatibility guidance.
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
ollama run firefunction-v2Sign in and add your RAM or GPU for compatibility guidance.
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
ollama run mathstralSign in and add your RAM or GPU for compatibility guidance.
A versatile model for AI software development scenarios, including code completion.
ollama run codegeex4Sign in and add your RAM or GPU for compatibility guidance.
A strong multi-lingual general language model with competitive performance to Llama 3.
ollama run glm4Sign in and add your RAM or GPU for compatibility guidance.
CodeQwen1.5 is a large language model pretrained on a large amount of code data.
ollama run codeqwenSign in and add your RAM or GPU for compatibility guidance.
A strong, economical, and efficient Mixture-of-Experts language model.
ollama run deepseek-v2Sign in and add your RAM or GPU for compatibility guidance.
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
ollama run ayaSign in and add your RAM or GPU for compatibility guidance.
Meta Llama 3: The most capable openly available LLM to date
ollama run llama3Sign in and add your RAM or GPU for compatibility guidance.
Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
ollama run falcon2Sign in and add your RAM or GPU for compatibility guidance.
Yi 1.5 is a high-performing, bilingual language model.
ollama run yiSign in and add your RAM or GPU for compatibility guidance.
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
ollama run llama3-chatqaSign in and add your RAM or GPU for compatibility guidance.
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
ollama run dolphin-llama3Sign in and add your RAM or GPU for compatibility guidance.
A new small LLaVA model fine-tuned from Phi 3 Mini.
ollama run llava-phi3Sign in and add your RAM or GPU for compatibility guidance.
moondream2 is a small vision language model designed to run efficiently on edge devices.
ollama run moondreamSign in and add your RAM or GPU for compatibility guidance.
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
ollama run llava-llama3Sign in and add your RAM or GPU for compatibility guidance.
Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.
ollama run stablelm2Sign in and add your RAM or GPU for compatibility guidance.
Embedding models on very large sentence level datasets.
ollama run all-minilmSign in and add your RAM or GPU for compatibility guidance.
State-of-the-art large embedding model from mixedbread.ai
ollama run mxbai-embed-largeSign in and add your RAM or GPU for compatibility guidance.
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
ollama run llama3-gradientSign in and add your RAM or GPU for compatibility guidance.
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
ollama run qwenSign in and add your RAM or GPU for compatibility guidance.
A suite of text embedding models by Snowflake, optimized for performance.
ollama run snowflake-arctic-embedSign in and add your RAM or GPU for compatibility guidance.
DBRX is an open, general-purpose LLM created by Databricks.
ollama run dbrxSign in and add your RAM or GPU for compatibility guidance.
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
ollama run wizardlm2Sign in and add your RAM or GPU for compatibility guidance.
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
ollama run zephyrSign in and add your RAM or GPU for compatibility guidance.
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
ollama run gemmaSign in and add your RAM or GPU for compatibility guidance.
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
ollama run dolphincoderSign in and add your RAM or GPU for compatibility guidance.
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
ollama run starling-lmSign in and add your RAM or GPU for compatibility guidance.
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
ollama run dolphin-mistralSign in and add your RAM or GPU for compatibility guidance.
Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.
ollama run stable-codeSign in and add your RAM or GPU for compatibility guidance.
A high-performing open embedding model with a large token context window.
ollama run nomic-embed-textSign in and add your RAM or GPU for compatibility guidance.
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
ollama run llavaSign in and add your RAM or GPU for compatibility guidance.
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
ollama run sqlcoderSign in and add your RAM or GPU for compatibility guidance.
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
ollama run tinydolphinSign in and add your RAM or GPU for compatibility guidance.
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
ollama run duckdb-nsqlSign in and add your RAM or GPU for compatibility guidance.
Nexus Raven is a 13B instruction tuned model for function calling tasks.
ollama run nexusravenSign in and add your RAM or GPU for compatibility guidance.
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
ollama run megadolphinSign in and add your RAM or GPU for compatibility guidance.
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
ollama run openchatSign in and add your RAM or GPU for compatibility guidance.
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
ollama run llama-proSign in and add your RAM or GPU for compatibility guidance.
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
ollama run phiSign in and add your RAM or GPU for compatibility guidance.
State-of-the-art code generation model
ollama run wizardcoderSign in and add your RAM or GPU for compatibility guidance.
The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
ollama run nous-hermes2Sign in and add your RAM or GPU for compatibility guidance.
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
ollama run tinyllamaSign in and add your RAM or GPU for compatibility guidance.
A 7B chat model fine-tuned with high-quality data and based on Zephyr.
ollama run notusSign in and add your RAM or GPU for compatibility guidance.
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
ollama run openhermesSign in and add your RAM or GPU for compatibility guidance.
A top-performing mixture of experts model, fine-tuned with high-quality data.
ollama run notuxSign in and add your RAM or GPU for compatibility guidance.
Code generation model based on Code Llama.
ollama run phind-codellamaSign in and add your RAM or GPU for compatibility guidance.
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
ollama run deepseek-coderSign in and add your RAM or GPU for compatibility guidance.
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
ollama run llama2Sign in and add your RAM or GPU for compatibility guidance.
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
ollama run stablelm-zephyrSign in and add your RAM or GPU for compatibility guidance.
Uncensored Llama2 based model with support for a 16K context window.
ollama run everythinglmSign in and add your RAM or GPU for compatibility guidance.
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
ollama run dolphin-phiSign in and add your RAM or GPU for compatibility guidance.
A fine-tuned model based on Mistral with good coverage of domain and language.
ollama run neural-chatSign in and add your RAM or GPU for compatibility guidance.
Model focused on math and logic problems
ollama run wizard-mathSign in and add your RAM or GPU for compatibility guidance.
A compact, yet powerful 10.7B large language model designed for single-turn conversation.
ollama run solarSign in and add your RAM or GPU for compatibility guidance.
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
ollama run bakllavaSign in and add your RAM or GPU for compatibility guidance.
An advanced language model crafted with 2 trillion bilingual tokens.
ollama run deepseek-llmSign in and add your RAM or GPU for compatibility guidance.
🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.
ollama run magicoderSign in and add your RAM or GPU for compatibility guidance.
Open-source medical large language model adapted from Llama 2 to the medical domain.
ollama run meditronSign in and add your RAM or GPU for compatibility guidance.
Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.
ollama run orca2Sign in and add your RAM or GPU for compatibility guidance.
A robust conversational model designed to be used for both chat and instruct use cases.
ollama run alfredSign in and add your RAM or GPU for compatibility guidance.
A language model created by combining two fine-tuned Llama 2 70B models into one.
ollama run goliathSign in and add your RAM or GPU for compatibility guidance.
An extension of Llama 2 that supports a context of up to 128k tokens.
ollama run yarn-llama2Sign in and add your RAM or GPU for compatibility guidance.
Conversational model based on Llama 2 that performs competitively on various benchmarks.
ollama run xwinlmSign in and add your RAM or GPU for compatibility guidance.
An extension of Mistral to support context windows of 64K or 128K.
ollama run yarn-mistralSign in and add your RAM or GPU for compatibility guidance.
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
ollama run mistralliteSign in and add your RAM or GPU for compatibility guidance.
General use model based on Llama 2.
ollama run wizardlmSign in and add your RAM or GPU for compatibility guidance.
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
ollama run stable-belugaSign in and add your RAM or GPU for compatibility guidance.
General use models based on Llama and Llama 2 from Nous Research.
ollama run nous-hermesSign in and add your RAM or GPU for compatibility guidance.
A high-performing code instruct model created by merging two existing code models.
ollama run codeboogaSign in and add your RAM or GPU for compatibility guidance.
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
ollama run open-orca-platypus2Sign in and add your RAM or GPU for compatibility guidance.
Great code generation model based on Llama2.
ollama run codeupSign in and add your RAM or GPU for compatibility guidance.
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
ollama run medllama2Sign in and add your RAM or GPU for compatibility guidance.
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
ollama run orca-miniSign in and add your RAM or GPU for compatibility guidance.
Uncensored Llama 2 model by George Sung and Jarrad Hope.
ollama run llama2-uncensoredSign in and add your RAM or GPU for compatibility guidance.
Llama 2 based model fine tuned to improve Chinese dialogue ability.
ollama run llama2-chineseSign in and add your RAM or GPU for compatibility guidance.
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
ollama run wizard-vicunaSign in and add your RAM or GPU for compatibility guidance.
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
ollama run wizard-vicuna-uncensoredSign in and add your RAM or GPU for compatibility guidance.
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
ollama run vicunaSign in and add your RAM or GPU for compatibility guidance.
Uncensored version of Wizard LM model
ollama run wizardlm-uncensoredSign in and add your RAM or GPU for compatibility guidance.
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
ollama run falconSign in and add your RAM or GPU for compatibility guidance.
StarCoder is a code generation model trained on 80+ programming languages.
ollama run starcoderSign in and add your RAM or GPU for compatibility guidance.
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
ollama run samantha-mistralSign in and add your RAM or GPU for compatibility guidance.
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
ollama run mistral-openorcaSign in and add your RAM or GPU for compatibility guidance.
Your saved list is empty.
Browse modelsSaved models, selected tags, and notes are private account records protected per user.