gemma4
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.
VisionToolsThinkingAudioCloude2be4b12b26b31b
ollama run gemma4ailocal.click
Click & build with ai open models, on your computer.
ollama run gemma3local AI starts here235 base models
Official library directory
Find a model
Base models from Ollama’s official library. Confirm exact variants, sizes, and licenses on Ollama.
235 models
qwen3.6
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
VisionToolsThinking27b35b
ollama run qwen3.6laguna-s-2.1
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
ToolsThinking
ollama run laguna-s-2.1laguna-xs-2.1
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.
ToolsThinking
ollama run laguna-xs-2.1ornith-1.5
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
Vision9b35b397b
ollama run ornith-1.5qwen3.8
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
VisionToolsThinking27b
ollama run qwen3.8muse-glimmer
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.
VisionToolsThinking30b
ollama run muse-glimmerdeepseek-v4-pro
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
ToolsThinkingCloud
ollama run deepseek-v4-pronemotron-3.5-lightning
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
ToolsThinking30b
ollama run nemotron-3.5-lightningdeepseek-v4-flash
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.
ToolsThinkingCloud
ollama run deepseek-v4-flashkimi-k3
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
VisionToolsThinkingCloud
ollama run kimi-k3laguna-xs.2
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.
ToolsThinking
ollama run laguna-xs.2ornith
A self-improving family of open-source models for agentic coding
Tools9b35b
ollama run ornithnorth-mini-code-1.0
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.
ToolsThinking
ollama run north-mini-code-1.0glm-5.2
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
ToolsThinkingCloud
ollama run glm-5.2kimi-k2.7-code
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.
VisionToolsThinkingCloud
ollama run kimi-k2.7-codegranite4.1-guardian
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.
ToolsThinking8b
ollama run granite4.1-guardianglm-4.7-flash
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
ToolsThinking
ollama run glm-4.7-flashnemotron-3-ultra
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
ToolsThinkingCloud
ollama run nemotron-3-ultraminicpm-v4.5
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
Vision8b
ollama run minicpm-v4.5minicpm-v4.6
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
Vision1b
ollama run minicpm-v4.6minimax-m3
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
VisionToolsThinkingCloud
ollama run minimax-m3lfm2.5
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
ToolsThinking8b
ollama run lfm2.5qwen3.5
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
VisionToolsThinkingCloud0.8b2b4b9b27b35b122b
ollama run qwen3.5granite4.1
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.
Tools3b8b30b
ollama run granite4.1mistral-medium-3.5
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.
VisionToolsThinking128b
ollama run mistral-medium-3.5nemotron3
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.
VisionToolsThinking33b
ollama run nemotron3kimi-k2.6
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.
VisionToolsThinkingCloud
ollama run kimi-k2.6medgemma
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
Vision4b27b
ollama run medgemmamedgemma1.5
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
Vision4b
ollama run medgemma1.5glm-5.1
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.
ToolsThinkingCloud
ollama run glm-5.1nemotron-cascade-2
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
ToolsThinking30b
ollama run nemotron-cascade-2minimax-m2.7
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
ToolsThinkingCloud
ollama run minimax-m2.7nemotron-3-nano
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
ToolsThinkingCloud4b30b
ollama run nemotron-3-nanonemotron-3-super
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.
ToolsThinkingCloud120b
ollama run nemotron-3-superlfm2
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.
Tools24b
ollama run lfm2qwen3-coder-next
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
Tools
ollama run qwen3-coder-nextglm-ocr
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
VisionTools
ollama run glm-ocrlfm2.5-thinking
LFM2.5 is a new family of hybrid models designed for on-device deployment.
ToolsThinking1.2b
ollama run lfm2.5-thinkingtranslategemma
A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
Vision4b12b27b
ollama run translategemmafunctiongemma
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
Tools270m
ollama run functiongemmaolmo-3.1
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.
ToolsThinking32b
ollama run olmo-3.1olmo-3
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.
ToolsThinking7b32b
ollama run olmo-3devstral-small-2
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
VisionTools24b
ollama run devstral-small-2ministral-3
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
VisionTools3b8b14b
ollama run ministral-3devstral-2
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
Tools123b
ollama run devstral-2nomic-embed-text-v2-moe
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
ollama run nomic-embed-text-v2-moernj-1
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.
Tools8b
ollama run rnj-1qwen3-next
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
ToolsThinking80b
ollama run qwen3-nextmistral-large-3
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
VisionToolsCloud
ollama run mistral-large-3deepseek-ocr
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
Vision3b
ollama run deepseek-ocrcogito-2.1
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
671b
ollama run cogito-2.1qwen3-vl
The most powerful vision-language model in the Qwen model family to date.
VisionToolsThinking2b4b8b30b32b235b
ollama run qwen3-vlgranite4
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
Tools350m1b3b
ollama run granite4gpt-oss-safeguard
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
ToolsThinking20b120b
ollama run gpt-oss-safeguardqwen3
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
ToolsThinking0.6b1.7b4b8b14b30b32b235b
ollama run qwen3gpt-oss
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
ToolsThinkingCloud20b120b
ollama run gpt-ossdeepseek-v3.1
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
ToolsThinking671b
ollama run deepseek-v3.1qwen3-embedding
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
0.6b4b8b
ollama run qwen3-embeddingqwen3-coder
Alibaba's performant long context models for agentic and coding tasks.
Tools30b480b
ollama run qwen3-coderembeddinggemma
EmbeddingGemma is a 300M parameter embedding model from Google.
300m
ollama run embeddinggemmagemma3
The current, most capable model that runs on a single GPU.
Vision270m1b4b12b27b
ollama run gemma3mistral-nemo
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
Tools12b
ollama run mistral-nemomistral
The 7B model released by Mistral AI, updated to version 0.3.
Tools7b
ollama run mistraldevstral
Devstral: the best open source model for coding agents
Tools24b
ollama run devstraldeepseek-r1
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
ToolsThinking1.5b7b8b14b32b70b671b
ollama run deepseek-r1gemma3n
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
e2be4b
ollama run gemma3nmistral-small3.2
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
VisionTools24b
ollama run mistral-small3.2magistral
Magistral is a small, efficient reasoning model with 24B parameters.
ToolsThinking24b
ollama run magistralllama4
Meta's latest collection of multimodal models.
VisionTools16x17b128x17b
ollama run llama4qwen2.5-coder
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
Tools0.5b1.5b3b7b14b32b
ollama run qwen2.5-coderqwen2.5vl
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
Vision3b7b32b72b
ollama run qwen2.5vlllama3.2-vision
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
Vision11b90b
ollama run llama3.2-visionphi4-reasoning
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
14b
ollama run phi4-reasoningphi4-mini-reasoning
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
3.8b
ollama run phi4-mini-reasoninggranite3.3
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
Tools2b8b
ollama run granite3.3deepcoder
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
1.5b14b
ollama run deepcodercogito
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.
Tools3b8b14b32b70b
ollama run cogitomistral-small3.1
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.
VisionTools24b
ollama run mistral-small3.1openthinker
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b32b
ollama run openthinkerexaone-deep
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.
2.4b7.8b32b
ollama run exaone-deepqwq
QwQ is the reasoning model of the Qwen series.
Tools32b
ollama run qwqcommand-a
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
Tools111b
ollama run command-acommand-r7b-arabic
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.
Tools7b
ollama run command-r7b-arabicphi4-mini
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
Tools3.8b
ollama run phi4-minigranite3.2-vision
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.
VisionTools2b
ollama run granite3.2-visiongranite3.2
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
Tools2b8b
ollama run granite3.2r1-1776
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
70b671b
ollama run r1-1776deepscaler
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.
1.5b
ollama run deepscalermistral-small
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
Tools22b24b
ollama run mistral-smallgranite3.1-dense
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.
Tools2b8b
ollama run granite3.1-densegranite3.1-moe
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
Tools1b3b
ollama run granite3.1-moecommand-r7b
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.
Tools7b
ollama run command-r7bdeepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
671b
ollama run deepseek-v3olmo2
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.
7b13b
ollama run olmo2phi4
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
14b
ollama run phi4dolphin3
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.
8b
ollama run dolphin3smallthinker
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
3b
ollama run smallthinkertulu3
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
8b70b
ollama run tulu3mixtral
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
Tools8x7b8x22b
ollama run mixtraldolphin-mixtral
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
8x7b8x22b
ollama run dolphin-mixtralnous-hermes2-mixtral
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
8x7b
ollama run nous-hermes2-mixtralgranite-embedding
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.
30m278m
ollama run granite-embeddingfalcon3
A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
1b3b7b10b
ollama run falcon3hermes3
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
Tools3b8b70b405b
ollama run hermes3exaone3.5
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.
2.4b7.8b32b
ollama run exaone3.5llama3.3
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
Tools70b
ollama run llama3.3snowflake-arctic-embed2
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
568m
ollama run snowflake-arctic-embed2marco-o1
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
7b
ollama run marco-o1sailor2
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
1b8b20b
ollama run sailor2llama3.1
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
Tools8b70b405b
ollama run llama3.1mistral-large
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.
Tools123b
ollama run mistral-largegranite3-guardian
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
2b8b
ollama run granite3-guardiangranite3-dense
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.
Tools2b8b
ollama run granite3-densegranite3-moe
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
Tools1b3b
ollama run granite3-moeopencoder
OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
1.5b8b
ollama run opencoderminicpm-v
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
Vision8b
ollama run minicpm-vathene-v2
Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
Tools72b
ollama run athene-v2smollm2
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
Tools135m360m1.7b
ollama run smollm2aya-expanse
Cohere For AI's language models trained to perform well across 23 different languages.
Tools8b32b
ollama run aya-expansenemotron
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.
Tools70b
ollama run nemotronshieldgemma
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.
2b9b27b
ollama run shieldgemmallama-guard3
Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.
1b8b
ollama run llama-guard3llama3.2
Meta's Llama 3.2 goes small with 1B and 3B models.
Tools1b3b
ollama run llama3.2qwen2.5
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.
Tools0.5b1.5b3b7b14b32b72b
ollama run qwen2.5solar-pro
Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU
22b
ollama run solar-pronemotron-mini
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
Tools4b
ollama run nemotron-minibespoke-minicheck
A state-of-the-art fact-checking model developed by Bespoke Labs.
7b
ollama run bespoke-minicheckdeepseek-v2.5
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
236b
ollama run deepseek-v2.5reader-lm
A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
0.5b1.5b
ollama run reader-lmyi-coder
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.
1.5b9b
ollama run yi-coderqwen2
Qwen2 is a new series of large language models from Alibaba group
Tools0.5b1.5b7b72b
ollama run qwen2reflection
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.
70b
ollama run reflectionstarcoder2
StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
3b7b15b
ollama run starcoder2deepseek-coder-v2
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
16b236b
ollama run deepseek-coder-v2phi3.5
A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
3.8b
ollama run phi3.5codestral
Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
22b
ollama run codestralgranite-code
A family of open foundation models by IBM for Code Intelligence
3b8b20b34b
ollama run granite-codecommand-r-plus
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
Tools104b
ollama run command-r-pluscommand-r
Command R is a Large Language Model optimized for conversational interaction and long context tasks.
Tools35b
ollama run command-rqwen2-math
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).
1.5b7b72b
ollama run qwen2-mathsmollm
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
135m360m1.7b
ollama run smollminternlm2
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
1m1.8b7b20b
ollama run internlm2bge-m3
BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
567m
ollama run bge-m3paraphrase-multilingual
Sentence-transformers model that can be used for tasks like clustering or semantic search.
278m
ollama run paraphrase-multilingualbge-large
Embedding model from BAAI mapping texts to vectors.
335m
ollama run bge-largegemma2
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
2b9b27b
ollama run gemma2phi3
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
3.8b14b
ollama run phi3llama3-groq-tool-use
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
Tools8b70b
ollama run llama3-groq-tool-usenuextract
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
3.8b
ollama run nuextractcodegemma
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.
2b7b
ollama run codegemmacodellama
A large language model that can use text prompts to generate and discuss code.
7b13b34b70b
ollama run codellamafirefunction-v2
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
Tools70b
ollama run firefunction-v2mathstral
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
7b
ollama run mathstralcodegeex4
A versatile model for AI software development scenarios, including code completion.
9b
ollama run codegeex4glm4
A strong multi-lingual general language model with competitive performance to Llama 3.
9b
ollama run glm4codeqwen
CodeQwen1.5 is a large language model pretrained on a large amount of code data.
7b
ollama run codeqwendeepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
16b236b
ollama run deepseek-v2aya
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
8b35b
ollama run ayallama3
Meta Llama 3: The most capable openly available LLM to date
8b70b
ollama run llama3falcon2
Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
11b
ollama run falcon2yi
Yi 1.5 is a high-performing, bilingual language model.
6b9b34b
ollama run yillama3-chatqa
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
8b70b
ollama run llama3-chatqadolphin-llama3
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.
8b70b
ollama run dolphin-llama3llava-phi3
A new small LLaVA model fine-tuned from Phi 3 Mini.
Vision3.8b
ollama run llava-phi3moondream
moondream2 is a small vision language model designed to run efficiently on edge devices.
Vision1.8b
ollama run moondreamllava-llama3
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
Vision8b
ollama run llava-llama3stablelm2
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.
1.6b12b
ollama run stablelm2all-minilm
Embedding models on very large sentence level datasets.
22m33m
ollama run all-minilmmxbai-embed-large
State-of-the-art large embedding model from mixedbread.ai
335m
ollama run mxbai-embed-largellama3-gradient
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
8b70b
ollama run llama3-gradientqwen
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
0.5b1.8b4b7b14b32b72b110b
ollama run qwensnowflake-arctic-embed
A suite of text embedding models by Snowflake, optimized for performance.
22m33m110m137m335m
ollama run snowflake-arctic-embeddbrx
DBRX is an open, general-purpose LLM created by Databricks.
132b
ollama run dbrxwizardlm2
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
7b8x22b
ollama run wizardlm2zephyr
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
7b141b
ollama run zephyrgemma
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
2b7b
ollama run gemmadolphincoder
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
7b15b
ollama run dolphincoderstarling-lm
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
7b
ollama run starling-lmdolphin-mistral
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
7b
ollama run dolphin-mistralstable-code
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.
3b
ollama run stable-codenomic-embed-text
A high-performing open embedding model with a large token context window.
ollama run nomic-embed-textllava
🌋 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.
Vision7b13b34b
ollama run llavasqlcoder
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
7b15b
ollama run sqlcodertinydolphin
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
1.1b
ollama run tinydolphinduckdb-nsql
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
7b
ollama run duckdb-nsqlnexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
13b
ollama run nexusravenmegadolphin
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
120b
ollama run megadolphinopenchat
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
7b
ollama run openchatllama-pro
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-prophi
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
2.7b
ollama run phiwizardcoder
State-of-the-art code generation model
33b
ollama run wizardcodernous-hermes2
The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
10.7b34b
ollama run nous-hermes2tinyllama
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
1.1b
ollama run tinyllamanotus
A 7B chat model fine-tuned with high-quality data and based on Zephyr.
7b
ollama run notusopenhermes
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
ollama run openhermesnotux
A top-performing mixture of experts model, fine-tuned with high-quality data.
8x7b
ollama run notuxphind-codellama
Code generation model based on Code Llama.
34b
ollama run phind-codellamadeepseek-coder
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
1.3b6.7b33b
ollama run deepseek-coderllama2
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
7b13b70b
ollama run llama2stablelm-zephyr
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
3b
ollama run stablelm-zephyreverythinglm
Uncensored Llama2 based model with support for a 16K context window.
13b
ollama run everythinglmdolphin-phi
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
2.7b
ollama run dolphin-phineural-chat
A fine-tuned model based on Mistral with good coverage of domain and language.
7b
ollama run neural-chatwizard-math
Model focused on math and logic problems
7b13b70b
ollama run wizard-mathsolar
A compact, yet powerful 10.7B large language model designed for single-turn conversation.
10.7b
ollama run solarbakllava
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
Vision7b
ollama run bakllavadeepseek-llm
An advanced language model crafted with 2 trillion bilingual tokens.
7b67b
ollama run deepseek-llmmagicoder
🎩 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.
7b
ollama run magicodermeditron
Open-source medical large language model adapted from Llama 2 to the medical domain.
7b70b
ollama run meditronorca2
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.
7b13b
ollama run orca2alfred
A robust conversational model designed to be used for both chat and instruct use cases.
40b
ollama run alfredgoliath
A language model created by combining two fine-tuned Llama 2 70B models into one.
ollama run goliathyarn-llama2
An extension of Llama 2 that supports a context of up to 128k tokens.
7b13b
ollama run yarn-llama2xwinlm
Conversational model based on Llama 2 that performs competitively on various benchmarks.
7b13b
ollama run xwinlmyarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
7b
ollama run yarn-mistralmistrallite
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
7b
ollama run mistrallitewizardlm
General use model based on Llama 2.
ollama run wizardlmstable-beluga
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
7b13b70b
ollama run stable-beluganous-hermes
General use models based on Llama and Llama 2 from Nous Research.
7b13b
ollama run nous-hermescodebooga
A high-performing code instruct model created by merging two existing code models.
34b
ollama run codeboogaopen-orca-platypus2
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
13b
ollama run open-orca-platypus2codeup
Great code generation model based on Llama2.
13b
ollama run codeupmedllama2
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
7b
ollama run medllama2orca-mini
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
3b7b13b70b
ollama run orca-minillama2-uncensored
Uncensored Llama 2 model by George Sung and Jarrad Hope.
7b70b
ollama run llama2-uncensoredllama2-chinese
Llama 2 based model fine tuned to improve Chinese dialogue ability.
7b13b
ollama run llama2-chinesewizard-vicuna
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
13b
ollama run wizard-vicunawizard-vicuna-uncensored
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
7b13b30b
ollama run wizard-vicuna-uncensoredvicuna
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
7b13b33b
ollama run vicunawizardlm-uncensored
Uncensored version of Wizard LM model
13b
ollama run wizardlm-uncensoredfalcon
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
7b40b180b
ollama run falconstarcoder
StarCoder is a code generation model trained on 80+ programming languages.
1b3b7b15b
ollama run starcodersamantha-mistral
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
7b
ollama run samantha-mistralmistral-openorca
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
7b
ollama run mistral-openorcaNo official-library models match those filters.