全球开源模型频道

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

ollama run mistral-nemo

经典 7B；生态与教程最多。

ollama run mistral:7b

中型开源；24GB 可 Q4/Q5。

ollama run mistral-small

经典 MoE；24–32GB 可量化运行。

ollama run mixtral

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

ollama run codestral

代理/coding 向开源；本地开发栈友好。

ollama run devstral

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

ollama run dolphin-mistral

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-mixtral

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-large

An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.

ollama run mistral-small3.2

大 MoE；多卡或 80GB 级。

123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

ollama run devstral-2

24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

ollama run devstral-small-2

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-3.5

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

ollama run mistral-openorca

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-small3.1

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

ollama run mistrallite

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

ollama run nous-hermes2-mixtral

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

ollama run samantha-mistral

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

ollama run yarn-mistral

A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

ollama run mistral-large-3