全球开源模型频道

OpenAI 开放权重线；本地/云双通道。

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

ollama run gpt-oss

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

ollama run aya

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 cogito

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

ollama run command-r

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 deepscaler

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

ollama run falcon

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

ollama run falcon3

Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.

ollama run gemini-3-flash-preview

A family of open foundation models by IBM for Code Intelligence

ollama run granite-code

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-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.

ollama run granite3.1-dense

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-moe

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 granite3.3

Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

ollama run granite4

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

ollama run hermes3

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 lfm2

LFM2.5 is a new family of hybrid models designed for on-device deployment.

ollama run lfm2.5-thinking

Magistral is a small, efficient reasoning model with 24B parameters.

ollama run magistral

MiniMax's M2-series model for coding, agentic workflows, and professional productivity.

ollama run minimax-m2.7

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

ollama run ministral-3

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

ollama run moondream

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

ollama run neural-chat

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

ollama run nous-hermes

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

ollama run nous-hermes2

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 olmo2

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 openchat

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

ollama run openhermes

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

ollama run openthinker

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

ollama run orca-mini

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

ollama run smollm

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

ollama run smollm2

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

ollama run sqlcoder

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-code

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 stablelm2

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

ollama run starcoder

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

ollama run starcoder2

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

ollama run vicuna

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

ollama run wizard-vicuna-uncensored

State-of-the-art code generation model

ollama run wizardcoder