全球开源模型频道

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

ollama run llama3.2

本地助手与 coding 入门标准；8–12GB Q4 舒适。

ollama run llama3.1:8b

R1 蒸馏小模型；消费级可跑推理风格。

ollama run deepseek-r1:8b

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 gemma4

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

ollama run llama3

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

ollama run qwen2.5-coder

开源旗舰对话质量；单卡 48GB+ Q4 或双 24GB TP。

ollama run llama3.3:70b

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

ollama run codellama

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

ollama run gemma

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

ollama run glm-ocr

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

ollama run gpt-oss

Llama 4 多模态 MoE 线；激活参数可控，机房/大显存。

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

ollama run llama2

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

ollama run minicpm-v

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

ollama run mistral-nemo

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

ollama run mxbai-embed-large

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

ollama run phi3

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

ollama run qwen

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

ollama run qwen2

The most powerful vision-language model in the Qwen model family to date.

ollama run qwen3-vl

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

ollama run qwen3.5

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

ollama run qwen3.6

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

ollama run tinyllama

更大 MoE；多卡/机房推理为主。

Ollama 默认 embedding 热门选择。

ollama pull nomic-embed-text

Embedding models on very large sentence level datasets.

ollama run all-minilm

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

ollama run aya

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 codegemma

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

ollama run codeqwen

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

ollama run codestral

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

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

ollama run deepseek-coder

An advanced language model crafted with 2 trillion bilingual tokens.

ollama run deepseek-llm

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

ollama run deepseek-v2

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-llama3

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

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

ollama run dolphin-phi