《ollama ：AI library》

AI Library

               Sort By                                Popular                                Newest                            

• deepseek-r1

  DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

  1.5b7b8b14b32b70b671b

  22.2M Pulls29 TagsUpdated 3 weeks ago

• llama3.3

  New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

  tools70b

  1.4M Pulls14 TagsUpdated 2 months ago

• phi4

  Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.

  14b

  840.4K Pulls5 TagsUpdated 7 weeks ago

• llama3.2

  Meta's Llama 3.2 goes small with 1B and 3B models.

  tools1b3b

  9.7M Pulls63 TagsUpdated 5 months ago

• llama3.1

  Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

  tools8b70b405b

  25.6M Pulls93 TagsUpdated 3 months ago

• nomic-embed-text

  A high-performing open embedding model with a large token context window.

  embedding

  17.7M Pulls3 TagsUpdated 12 months ago

• mistral

  The 7B model released by Mistral AI, updated to version 0.3.

  tools7b

  9.7M Pulls84 TagsUpdated 7 months ago

• llama3

  Meta Llama 3: The most capable openly available LLM to date

  8b70b

  7.5M Pulls68 TagsUpdated 9 months ago

• qwen2.5

  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

  4.8M Pulls133 TagsUpdated 5 months ago

• qwen

  Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters

  0.5b1.8b4b7b14b32b72b110b

  4.4M Pulls379 TagsUpdated 10 months ago

• gemma

  Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1

  2b7b

  4.4M Pulls102 TagsUpdated 10 months ago

• qwen2.5-coder

  The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

  tools0.5b1.5b3b7b14b32b

  4.3M Pulls196 TagsUpdated 3 months ago

• qwen2

  Qwen2 is a new series of large language models from Alibaba group

  tools0.5b1.5b7b72b

  4.1M Pulls97 TagsUpdated 5 months ago

• llava

  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

  3.7M Pulls98 TagsUpdated 13 months ago

• gemma2

  Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.

  2b9b27b

  3.1M Pulls94 TagsUpdated 7 months ago

• llama2

  Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

  7b13b70b

  3M Pulls102 TagsUpdated 14 months ago

• phi3

  Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.

  3.8b14b

  2.9M Pulls72 TagsUpdated 7 months ago

• codellama

  A large language model that can use text prompts to generate and discuss code.

  7b13b34b70b

  1.8M Pulls199 TagsUpdated 7 months ago

• mxbai-embed-large

  State-of-the-art large embedding model from mixedbread.ai

  embedding335m

  1.6M Pulls4 TagsUpdated 10 months ago

• llama3.2-vision

  Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

  vision11b90b

  1.4M Pulls9 TagsUpdated 3 months ago

• tinyllama

  The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

  1.1b

  1.3M Pulls36 TagsUpdated 14 months ago

• mistral-nemo

  A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

  tools12b

  1.2M Pulls17 TagsUpdated 6 months ago

• starcoder2

  StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

  3b7b15b

  892.4K Pulls67 TagsUpdated 5 months ago

• deepseek-coder-v2

  An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

  16b236b

  700.6K Pulls64 TagsUpdated 5 months ago

• deepseek-v3

  A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

  671b

  696.4K Pulls5 TagsUpdated 6 weeks ago

• snowflake-arctic-embed

  A suite of text embedding models by Snowflake, optimized for performance.

  embedding22m33m110m137m335m

  694.7K Pulls16 TagsUpdated 10 months ago

• llama2-uncensored

  Uncensored Llama 2 model by George Sung and Jarrad Hope.

  7b70b

  626.7K Pulls34 TagsUpdated 16 months ago

• deepseek-coder

  DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

  1.3b6.7b33b

  587K Pulls102 TagsUpdated 14 months ago

• mixtral

  A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

  tools8x7b8x22b

  573.8K Pulls70 TagsUpdated 2 months ago

• dolphin-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

  517.3K Pulls70 TagsUpdated 2 months ago

• codegemma

  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

  511.6K Pulls85 TagsUpdated 7 months ago

• openthinker

  A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

  7b32b

  505.6K Pulls9 TagsUpdated 2 weeks ago

• phi

  Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.

  2.7b

  493.5K Pulls18 TagsUpdated 14 months ago

• bge-m3

  BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.

  embedding567m

  490.9K Pulls3 TagsUpdated 6 months ago

• minicpm-v

  A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

  vision8b

  419K Pulls17 TagsUpdated 3 months ago

• llava-llama3

  A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

  vision8b

  386.6K Pulls4 TagsUpdated 9 months ago

• wizardlm2

  State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

  7b8x22b

  355.4K Pulls22 TagsUpdated 10 months ago

• dolphin-mistral

  The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

  7b

  323K Pulls120 TagsUpdated 11 months ago

• smollm2

  SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

  tools135m360m1.7b

  311.9K Pulls49 TagsUpdated 4 months ago

• all-minilm

  Embedding models on very large sentence level datasets.

  embedding22m33m

  303.3K Pulls10 TagsUpdated 10 months ago

• dolphin-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

  288.8K Pulls53 TagsUpdated 9 months ago

• command-r

  Command R is a Large Language Model optimized for conversational interaction and long context tasks.

  tools35b

  281.6K Pulls32 TagsUpdated 6 months ago

• orca-mini

  A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

  3b7b13b70b

  275.8K Pulls119 TagsUpdated 16 months ago

• dolphin3

  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

  272.4K Pulls5 TagsUpdated 8 weeks ago

• yi

  Yi 1.5 is a high-performing, bilingual language model.

  6b9b34b

  266K Pulls174 TagsUpdated 9 months ago

• hermes3

  Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research

  tools3b8b70b405b

  260.9K Pulls65 TagsUpdated 2 months ago

• phi3.5

  A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.

  3.8b

  246K Pulls17 TagsUpdated 5 months ago

• olmo2

  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

  240.9K Pulls9 TagsUpdated 7 weeks ago

• zephyr

  Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.

  7b141b

  237.3K Pulls40 TagsUpdated 10 months ago

• mistral-small

  Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.

  tools22b24b

  232.8K Pulls21 TagsUpdated 4 weeks ago

• codestral

  Codestral is Mistral AI’s first-ever code model designed for code generation tasks.

  22b

  223.2K Pulls17 TagsUpdated 6 months ago

• granite-code

  A family of open foundation models by IBM for Code Intelligence

  3b8b20b34b

  189.2K Pulls162 TagsUpdated 6 months ago

• starcoder

  StarCoder is a code generation model trained on 80+ programming languages.

  1b3b7b15b

  186.3K Pulls100 TagsUpdated 16 months ago

• smollm

  A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.

  135m360m1.7b

  181.8K Pulls94 TagsUpdated 6 months ago

• wizard-vicuna-uncensored

  Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.

  7b13b30b

  180.3K Pulls49 TagsUpdated 16 months ago

• vicuna

  General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.

  7b13b33b

  175.3K Pulls111 TagsUpdated 16 months ago

• mistral-openorca

  Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.

  7b

  166.4K Pulls17 TagsUpdated 16 months ago

• qwq

  QwQ is an experimental research model focused on advancing AI reasoning capabilities.

  tools32b

  163.9K Pulls5 TagsUpdated 3 months ago

• llama2-chinese

  Llama 2 based model fine tuned to improve Chinese dialogue ability.

  7b13b

  149.2K Pulls35 TagsUpdated 16 months ago

• openchat

  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

  144K Pulls50 TagsUpdated 13 months ago

• codegeex4

  A versatile model for AI software development scenarios, including code completion.

  9b

  138.2K Pulls17 TagsUpdated 7 months ago

• aya

  Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.

  8b35b

  134.9K Pulls33 TagsUpdated 9 months ago

• codeqwen

  CodeQwen1.5 is a large language model pretrained on a large amount of code data.

  7b

  130.6K Pulls30 TagsUpdated 8 months ago

• deepseek-llm

  An advanced language model crafted with 2 trillion bilingual tokens.

  7b67b

  130K Pulls64 TagsUpdated 14 months ago

• deepseek-v2

  A strong, economical, and efficient Mixture-of-Experts language model.

  16b236b

  124.5K Pulls34 TagsUpdated 8 months ago

• mistral-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

  123.6K Pulls32 TagsUpdated 3 months ago

• glm4

  A strong multi-lingual general language model with competitive performance to Llama 3.

  9b

  121.8K Pulls32 TagsUpdated 7 months ago

• nous-hermes2

  The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.

  10.7b34b

  121.4K Pulls33 TagsUpdated 14 months ago

• stable-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

  121K Pulls36 TagsUpdated 11 months ago

• openhermes

  OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.

  120.7K Pulls35 TagsUpdated 14 months ago

• qwen2-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

  119.3K Pulls52 TagsUpdated 6 months ago

• tinydolphin

  An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

  1.1b

  119.2K Pulls18 TagsUpdated 13 months ago

• command-r-plus

  Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

  tools104b

  119K Pulls21 TagsUpdated 6 months ago

• wizardcoder

  State-of-the-art code generation model

  33b

  116.4K Pulls67 TagsUpdated 14 months ago

• moondream

  moondream2 is a small vision language model designed to run efficiently on edge devices.

  vision1.8b

  111K Pulls18 TagsUpdated 9 months ago

• bakllava

  BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

  vision7b

  108.7K Pulls17 TagsUpdated 14 months ago

• stablelm2

  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

  107.2K Pulls84 TagsUpdated 10 months ago

• neural-chat

  A fine-tuned model based on Mistral with good coverage of domain and language.

  7b

  103.7K Pulls50 TagsUpdated 14 months ago

• reflection

  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

  103.1K Pulls17 TagsUpdated 5 months ago

• wizard-math

  Model focused on math and logic problems

  7b13b70b

  100.6K Pulls64 TagsUpdated 14 months ago

• llama3-gradient

  This model extends LLama-3 8B's context length from 8k to over 1m tokens.

  8b70b

  97.5K Pulls35 TagsUpdated 10 months ago

• llama3-chatqa

  A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

  8b70b

  95.8K Pulls35 TagsUpdated 9 months ago

• sqlcoder

  SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks

  7b15b

  92K Pulls48 TagsUpdated 13 months ago

• bge-large

  Embedding model from BAAI mapping texts to vectors.

  embedding335m

  85.5K Pulls3 TagsUpdated 6 months ago

• xwinlm

  Conversational model based on Llama 2 that performs competitively on various benchmarks.

  7b13b

  84K Pulls80 TagsUpdated 16 months ago

• dolphincoder

  A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.

  7b15b

  83.4K Pulls35 TagsUpdated 10 months ago

• nous-hermes

  General use models based on Llama and Llama 2 from Nous Research.

  7b13b

  81.9K Pulls63 TagsUpdated 16 months ago

• phind-codellama

  Code generation model based on Code Llama.

  34b

  81.1K Pulls49 TagsUpdated 14 months ago

• llava-phi3

  A new small LLaVA model fine-tuned from Phi 3 Mini.

  vision3.8b

  79.7K Pulls4 TagsUpdated 9 months ago

• granite3.1-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

  78.9K Pulls33 TagsUpdated 6 weeks ago

• solar

  A compact, yet powerful 10.7B large language model designed for single-turn conversation.

  10.7b

  78.5K Pulls32 TagsUpdated 14 months ago

• yarn-llama2

  An extension of Llama 2 that supports a context of up to 128k tokens.

  7b13b

  78.5K Pulls67 TagsUpdated 16 months ago

• starling-lm

  Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.

  7b

  77.1K Pulls36 TagsUpdated 11 months ago

• samantha-mistral

  A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.

  7b

  76.8K Pulls49 TagsUpdated 16 months ago

• athene-v2

  Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

  tools72b

  76.3K Pulls17 TagsUpdated 3 months ago

• yi-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

  76K Pulls67 TagsUpdated 5 months ago

• wizardlm

  General use model based on Llama 2.

  75.6K Pulls73 TagsUpdated 16 months ago

• internlm2

  InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.

  1m1.8b7b20b

  73.1K Pulls65 TagsUpdated 6 months ago

• falcon

  A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.

  7b40b180b

  69.5K Pulls38 TagsUpdated 16 months ago

• nemotron-mini

  A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

  tools4b

  68.3K Pulls17 TagsUpdated 5 months ago

• nemotron

  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

  66.2K Pulls17 TagsUpdated 4 months ago

• dolphin-phi

  2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

  2.7b

  64.7K Pulls15 TagsUpdated 14 months ago

• orca2

  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

  63.1K Pulls33 TagsUpdated 15 months ago

• deepscaler

  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

  62.6K Pulls5 TagsUpdated 2 weeks ago

• wizardlm-uncensored

  Uncensored version of Wizard LM model

  13b

  60.1K Pulls18 TagsUpdated 16 months ago

• stable-beluga

  Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.

  7b13b70b

  58.7K Pulls49 TagsUpdated 16 months ago

• granite3-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

  56.4K Pulls33 TagsUpdated 3 months ago

• llama3-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

  54.8K Pulls33 TagsUpdated 7 months ago

• paraphrase-multilingual

  Sentence-transformers model that can be used for tasks like clustering or semantic search.

  embedding278m

  50.1K Pulls3 TagsUpdated 6 months ago

• deepseek-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

  49.3K Pulls7 TagsUpdated 5 months ago

• medllama2

  Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

  7b

  47.1K Pulls17 TagsUpdated 16 months ago

• meditron

  Open-source medical large language model adapted from Llama 2 to the medical domain.

  7b70b

  46.8K Pulls22 TagsUpdated 15 months ago

• smallthinker

  A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

  3b

  46.4K Pulls5 TagsUpdated 2 months ago

• llama-pro

  An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

  45.4K Pulls33 TagsUpdated 13 months ago

• aya-expanse

  Cohere For AI's language models trained to perform well across 23 different languages.

  tools8b32b

  45.1K Pulls33 TagsUpdated 4 months ago

• yarn-mistral

  An extension of Mistral to support context windows of 64K or 128K.

  7b

  45K Pulls33 TagsUpdated 16 months ago

• granite3-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

  43.4K Pulls33 TagsUpdated 3 months ago

• nexusraven

  Nexus Raven is a 13B instruction tuned model for function calling tasks.

  13b

  41.4K Pulls32 TagsUpdated 13 months ago

• falcon3

  A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.

  1b3b7b10b

  40.3K Pulls17 TagsUpdated 2 months ago

• codeup

  Great code generation model based on Llama2.

  13b

  39.4K Pulls19 TagsUpdated 16 months ago

• nous-hermes2-mixtral

  The Nous Hermes 2 model from Nous Research, now trained over Mixtral.

  8x7b

  38.1K Pulls18 TagsUpdated 2 months ago

• everythinglm

  Uncensored Llama2 based model with support for a 16K context window.

  13b

  38K Pulls18 TagsUpdated 14 months ago

• shieldgemma

  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

  35.2K Pulls49 TagsUpdated 4 months ago

• granite3.1-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

  34.2K Pulls33 TagsUpdated 6 weeks ago

• snowflake-arctic-embed2

  Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.

  embedding568m

  34K Pulls3 TagsUpdated 2 months ago

• marco-o1

  An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).

  7b

  32.6K Pulls5 TagsUpdated 2 months ago

• mathstral

  MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.

  7b

  32.1K Pulls17 TagsUpdated 7 months ago

• falcon2

  Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.

  11b

  32K Pulls17 TagsUpdated 9 months ago

• magicoder

  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

  31.9K Pulls18 TagsUpdated 15 months ago

• stablelm-zephyr

  A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.

  3b

  31.7K Pulls17 TagsUpdated 14 months ago

• reader-lm

  A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.

  0.5b1.5b

  31.6K Pulls33 TagsUpdated 5 months ago

• solar-pro

  Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU

  22b

  31.5K Pulls18 TagsUpdated 5 months ago

• codebooga

  A high-performing code instruct model created by merging two existing code models.

  34b

  31.1K Pulls16 TagsUpdated 16 months ago

• duckdb-nsql

  7B parameter text-to-SQL model made by MotherDuck and Numbers Station.

  7b

  29.9K Pulls17 TagsUpdated 13 months ago

• mistrallite

  MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.

  7b

  29.7K Pulls17 TagsUpdated 16 months ago

• llama-guard3

  Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.

  1b8b

  29.6K Pulls33 TagsUpdated 4 months ago

• wizard-vicuna

  Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.

  13b

  29.4K Pulls17 TagsUpdated 16 months ago

• exaone3.5

  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

  26.7K Pulls13 TagsUpdated 2 months ago

• megadolphin

  MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.

  120b

  25.2K Pulls19 TagsUpdated 13 months ago

• nuextract

  A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.

  3.8b

  25.2K Pulls17 TagsUpdated 7 months ago

• opencoder

  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

  25.2K Pulls9 TagsUpdated 3 months ago

• notux

  A top-performing mixture of experts model, fine-tuned with high-quality data.

  8x7b

  24.2K Pulls18 TagsUpdated 14 months ago

• open-orca-platypus2

  Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

  13b

  23.7K Pulls17 TagsUpdated 16 months ago

• notus

  A 7B chat model fine-tuned with high-quality data and based on Zephyr.

  7b

  23.5K Pulls18 TagsUpdated 14 months ago

• goliath

  A language model created by combining two fine-tuned Llama 2 70B models into one.

  22.9K Pulls16 TagsUpdated 15 months ago

• command-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

  22.6K Pulls5 TagsUpdated 6 weeks ago

• bespoke-minicheck

  A state-of-the-art fact-checking model developed by Bespoke Labs.

  7b

  22.2K Pulls17 TagsUpdated 5 months ago

• tulu3

  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

  18.9K Pulls9 TagsUpdated 2 months ago

• firefunction-v2

  An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

  tools70b

  18.8K Pulls17 TagsUpdated 7 months ago

• granite-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.

  embedding30m278m

  18.8K Pulls6 TagsUpdated 2 months ago

• dbrx

  DBRX is an open, general-purpose LLM created by Databricks.

  132b

  18.3K Pulls7 TagsUpdated 10 months ago

• granite3-guardian

  The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.

  2b8b

  16.3K Pulls10 TagsUpdated 3 months ago

• alfred

  A robust conversational model designed to be used for both chat and instruct use cases.

  40b

  15.6K Pulls7 TagsUpdated 15 months ago

• r1-1776

  A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

  70b671b

  9,925 Pulls9 TagsUpdated 9 days ago

• sailor2

  Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.

  1b8b20b

  9,405 Pulls13 TagsUpdated 2 months ago

• phi4-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

  8,260 Pulls5 TagsUpdated 2 days ago

• granite3.2

  Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

  tools2b8b

  7,807 Pulls9 TagsUpdated 5 days ago

• granite3.2-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

  4,723 Pulls5 TagsUpdated 3 days ago

• command-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

  2,391 Pulls5 TagsUpdated 2 days ago

© 2025 Ollama