huihui_ai/Qwen3-Coder

huihui_ai/ Qwen3-Coder

681 Downloads Updated 7 months ago

This is not the ablation version. Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.

tools thinking 480b

ollama run huihui_ai/Qwen3-Coder

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/Qwen3-Coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/Qwen3-Coder',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/Qwen3-Coder',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model huihui_ai/Qwen3-Coder

Codex

Codex ollama launch codex --model huihui_ai/Qwen3-Coder

OpenCode

OpenCode ollama launch opencode --model huihui_ai/Qwen3-Coder

OpenClaw

OpenClaw ollama launch openclaw --model huihui_ai/Qwen3-Coder

Models

Name

4 models

Size

Context

Input

Qwen3-Coder:latest

175GB · 256K context window · Text · 7 months ago

Qwen3-Coder:latest

175GB

256K

Text

Qwen3-Coder:480b

175GB · 256K context window · Text · 7 months ago

Qwen3-Coder:480b latest

175GB

256K

Text

Readme

Template

The template used is Qwen3’s template, which may not be suitable for tool calls.

Parameter description

1. num_gpu
The value of num_gpu inside the model is 1, which means it defaults to loading one layer. All others will be loaded into CPU memory. You can modify num_gpu according to your GPU configuration.

/set parameter num_gpu 2

2. num_thread
“num_thread” refers to the number of cores in your computer, and it’s recommended to use half of that, Otherwise, the CPU will be at 100%.

/set parameter num_thread 32

3. num_ctx
“num_ctx” for ollama refers to the number of context slots or the number of contexts the model can maintain during inference.

/set parameter num_ctx 4096

References

Qwen/qwen3-coder

Donation

You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

### Template
The template used is Qwen3's template, which may not be suitable for tool calls.

#### Parameter description
**1. num_gpu**  
The value of `num_gpu` inside the model is 1, which means it defaults to loading one layer. All others will be loaded into CPU memory. You can modify `num_gpu` according to your GPU configuration.

```
/set parameter num_gpu 2
```
**2. num_thread**  
"num_thread" refers to the number of cores in your computer, and it's recommended to use half of that, Otherwise, the CPU will be at 100%.
```
/set parameter num_thread 32
```
**3. num_ctx**  
"num_ctx" for ollama refers to the number of context slots or the number of contexts the model can maintain during inference.
```
/set parameter num_ctx 4096
```

### References

[Qwen/qwen3-coder](https://huggingface.co/collections/Qwen/qwen3-coder-687fc861e53c939e52d52d10)

### Donation

You can follow [x.com/support_huihui](https://x.com/support_huihui) to get the latest model information from huihui.ai.

##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
```
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
```

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)