全球开源模型频道

中文本地日用首选之一；8GB 卡 Q4 可跑。

ollama run qwen2.5:7b

R1 蒸馏小模型；消费级可跑推理风格。

ollama run deepseek-r1:8b

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

ollama run qwen2.5-coder

Qwen3 单卡旗舰向；强推理与中文。

ollama run qwen3:32b

4090 24GB 本地强 coding / 中文综合甜点。

ollama run qwen2.5:32b

Qwen3 小参数；思考/非思考模式按发行版。

ollama run qwen3:8b

接近商用中文质量；48GB+ 或双卡。

ollama run qwen2.5:72b

16GB 卡甜点；中文写作与中等 coding。

ollama run qwen2.5:14b

代码专用线；本地 Agent/IDE 后端常见。

ollama run qwen3-coder

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

本地截图/文档视觉问答。

ollama run qwen2-vl

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

ollama run codeqwen

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

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

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).

ollama run qwen2-math

Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

ollama run qwen2.5vl

Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.

ollama run qwen3-coder-next

Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes

ollama run qwen3-embedding

QwQ is the reasoning model of the Qwen series.

ollama run qwq

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

ollama run qwen3-next

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

ollama run smallthinker

Hugging Face GGUF · downloads ~3,816,684. Repo: unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Hugging Face GGUF · downloads ~1,892,654. Repo: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Hugging Face GGUF · downloads ~1,372,285. Repo: DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

Hugging Face GGUF · downloads ~1,171,565. Repo: unsloth/Qwen3.5-4B-GGUF

Hugging Face GGUF · downloads ~1,206,350. Repo: unsloth/Qwen3.6-27B-MTP-GGUF

Hugging Face GGUF · downloads ~1,001,923. Repo: unsloth/Qwen3.5-9B-GGUF

Hugging Face GGUF · downloads ~797,066. Repo: Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF

Hugging Face GGUF · downloads ~872,509. Repo: unsloth/Qwen3.6-35B-A3B-GGUF

Hugging Face GGUF · downloads ~715,238. Repo: unsloth/Qwen3.6-27B-GGUF

Hugging Face GGUF · downloads ~563,938. Repo: unsloth/Qwen-AgentWorld-35B-A3B-GGUF

Hugging Face GGUF · downloads ~627,507. Repo: mradermacher/Qwen3-VL-8B-Instruct-abliterated-GGUF

Hugging Face GGUF · downloads ~636,347. Repo: unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Hugging Face GGUF · downloads ~438,154. Repo: bartowski/Qwen_Qwen3.6-35B-A3B-GGUF

Hugging Face GGUF · downloads ~484,939. Repo: lmstudio-community/Qwen3.5-9B-GGUF

Hugging Face GGUF · downloads ~497,271. Repo: HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive