kavai/ qwen3.5-GPT5

921 Downloads Updated 3 days ago

Qwen 3.5 is a family of open-source models that delivers exceptional utility and performance for tool calling and Agentic abilities. Smaller Models may suffer from slower speeds.

vision tools thinking 0.8b 2b 4b 9b 27b 35b 122b

ollama run kavai/qwen3.5-GPT5:0.8b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kavai/qwen3.5-GPT5:0.8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kavai/qwen3.5-GPT5:0.8b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kavai/qwen3.5-GPT5:0.8b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model kavai/qwen3.5-GPT5:0.8b

Codex

Codex ollama launch codex --model kavai/qwen3.5-GPT5:0.8b

OpenCode

OpenCode ollama launch opencode --model kavai/qwen3.5-GPT5:0.8b

OpenClaw

OpenClaw ollama launch openclaw --model kavai/qwen3.5-GPT5:0.8b

Models

Name

21 models

Size

Context

Input

qwen3.5-GPT5:0.8b

1.0GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:0.8b

1.0GB

256K

Text, Image

qwen3.5-GPT5:2b

2.7GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:2b

2.7GB

256K

Text, Image

qwen3.5-GPT5:4b

3.4GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:4b

3.4GB

256K

Text, Image

qwen3.5-GPT5:9b

6.6GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:9b

6.6GB

256K

Text, Image

qwen3.5-GPT5:27b

17GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:27b

17GB

256K

Text, Image

qwen3.5-GPT5:35b

24GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:35b

24GB

256K

Text, Image

qwen3.5-GPT5:122b

81GB · 256K context window · Text, Image · 3 days ago

qwen3.5-GPT5:122b

81GB

256K

Text, Image

Readme

Qwen3.5-GPT5

Qwen3.5-GPT5 builds on the strong foundation of the Qwen3.5 family with a refined system prompt optimized for reasoning clarity, instruction adherence, and developer-centric workflows. The goal is to provide a drop-in upgrade that improves consistency, structured outputs, and general usefulness across coding, analysis, and conversational tasks. The model is has equal of if not better Tool calling capabilities as the base model.

Highlights

Improved reasoning stability and reduced hallucination
Stronger instruction following and formatting discipline
Better performance in coding and technical explanation tasks
Optimized for developer workflows and tool usage
Lightweight system-layer modification (no weight changes)

Model Variants

122b — Maximum capability and reasoning performance
35b — Balanced performance and efficiency
9b — Fast and lightweight deployment

Usage

ollama run kavai/qwen3.5-GPT5:122b

or

ollama run kavai/qwen3.5-GPT5:35b

Design Philosophy

This release focuses on practical usability improvements without modifying base model weights. By injecting an optimized system layer, Qwen3.5-GPT5 enhances behavioral alignment while preserving the strong general intelligence of the original Qwen3.5 models.

Benchmarks

Formal benchmark results are coming soon. Model speeds may be slower than expected due to the system prompt.

Notes

No architectural changes to base model
Fully compatible with existing Qwen3.5 tooling
Suitable for chat, coding, and reasoning workload.
Recommended to use on GPU.

License

Follows the original Qwen3.5 model license.

# Qwen3.5-GPT5

Qwen3.5-GPT5 builds on the strong foundation of the Qwen3.5 family with a refined system prompt optimized for reasoning clarity, instruction adherence, and developer-centric workflows. The goal is to provide a drop-in upgrade that improves consistency, structured outputs, and general usefulness across coding, analysis, and conversational tasks. The model is has equal of if not better Tool calling capabilities as the base model.

## Highlights

* Improved reasoning stability and reduced hallucination
* Stronger instruction following and formatting discipline
* Better performance in coding and technical explanation tasks
* Optimized for developer workflows and tool usage
* Lightweight system-layer modification (no weight changes)

## Model Variants

* `122b` — Maximum capability and reasoning performance
* `35b` — Balanced performance and efficiency
* `9b` — Fast and lightweight deployment

## Usage

```bash
ollama run kavai/qwen3.5-GPT5:122b
```

or

```bash
ollama run kavai/qwen3.5-GPT5:35b
```

## Design Philosophy

This release focuses on practical usability improvements without modifying base model weights. By injecting an optimized system layer, Qwen3.5-GPT5 enhances behavioral alignment while preserving the strong general intelligence of the original Qwen3.5 models.

## Benchmarks

Formal benchmark results are coming soon. Model speeds may be slower than expected due to the system prompt.

## Notes

* No architectural changes to base model
* Fully compatible with existing Qwen3.5 tooling
* Suitable for chat, coding, and reasoning workload.
* Recommended to use on GPU.

## License

Follows the original Qwen3.5 model license.

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