kavai/ qwen3.5-Gemini-Design

500 Downloads Updated 3 days ago

Qwen3.5-Gemini-Design enhances the models with an optimized system prompt for better reasoning, coding, and instruction-following performance. Smaller Models may suffer from slower speeds.

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

ollama run kavai/qwen3.5-Gemini-Design:0.8b

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

from ollama import chat

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

import ollama from 'ollama'

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

Applications

Claude Code

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

Codex

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

OpenCode

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

OpenClaw

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

Models

Name

14 models

Size

Context

Input

qwen3.5-Gemini-Design:0.8b

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

qwen3.5-Gemini-Design:0.8b

1.0GB

256K

Text, Image

qwen3.5-Gemini-Design:2b

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

qwen3.5-Gemini-Design:2b

2.7GB

256K

Text, Image

qwen3.5-Gemini-Design:4b

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

qwen3.5-Gemini-Design:4b

3.4GB

256K

Text, Image

qwen3.5-Gemini-Design:9b

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

qwen3.5-Gemini-Design:9b

6.6GB

256K

Text, Image

qwen3.5-Gemini-Design:27b

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

qwen3.5-Gemini-Design:27b

17GB

256K

Text, Image

qwen3.5-Gemini-Design:35b

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

qwen3.5-Gemini-Design:35b

24GB

256K

Text, Image

qwen3.5-Gemini-Design:122b

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

qwen3.5-Gemini-Design:122b

81GB

256K

Text, Image

Readme

Qwen3.5-Gemini-Design

Summary: Qwen3.5-Gemini-Design is a prompt-optimized variant of the Qwen3.5 family focused on structured design workflows, layout reasoning, and high-quality visual and UI generation prompts.

Overview

Qwen3.5-Gemini-Design builds on the strong foundation of the Qwen3.5 models with a refined system prompt tailored for design-oriented tasks. The goal is to improve performance in UI/UX generation, layout planning, visual prompt engineering, and structured creative workflows while maintaining the reasoning strength of the base model.

Highlights

Optimized for UI/UX and product design workflows
Stronger structured output for layout and component descriptions
Improved prompt generation for Gemini-style design pipelines
Better reasoning for visual hierarchy and spacing logic
Lightweight system-layer modification (no weight changes)

Use Cases

UI/UX wireframe generation
Figma and layout prompt drafting
Design system creation
Component hierarchy planning
Landing page structure generation
Visual prompt engineering for Gemini models

Usage

ollama run kavai/qwen3.5-Gemini-Design

Design Philosophy

This release focuses on improving design-centric reasoning through prompt engineering rather than modifying model weights. By injecting a structured design-focused system layer, Qwen3.5-Gemini-Design enhances layout understanding, component grouping, and visual instruction clarity.

Benchmarks

Formal design-task benchmarks coming soon. Model speeds may be slower than expected due to the system prompt.

Notes

No architectural changes to base model
Fully compatible with Qwen3.5 tooling
Optimized for design and creative workflows
Works well with Gemini-style prompt pipelines
Recommended to use on GPU

License

Follows the original Qwen3.5 model license.

# Qwen3.5-Gemini-Design

**Summary:** Qwen3.5-Gemini-Design is a prompt-optimized variant of the Qwen3.5 family focused on structured design workflows, layout reasoning, and high-quality visual and UI generation prompts.

## Overview

Qwen3.5-Gemini-Design builds on the strong foundation of the Qwen3.5 models with a refined system prompt tailored for design-oriented tasks. The goal is to improve performance in UI/UX generation, layout planning, visual prompt engineering, and structured creative workflows while maintaining the reasoning strength of the base model.

## Highlights

* Optimized for UI/UX and product design workflows
* Stronger structured output for layout and component descriptions
* Improved prompt generation for Gemini-style design pipelines
* Better reasoning for visual hierarchy and spacing logic
* Lightweight system-layer modification (no weight changes)

## Use Cases

* UI/UX wireframe generation
* Figma and layout prompt drafting
* Design system creation
* Component hierarchy planning
* Landing page structure generation
* Visual prompt engineering for Gemini models

## Usage

```bash
ollama run kavai/qwen3.5-Gemini-Design
```

## Design Philosophy

This release focuses on improving design-centric reasoning through prompt engineering rather than modifying model weights. By injecting a structured design-focused system layer, Qwen3.5-Gemini-Design enhances layout understanding, component grouping, and visual instruction clarity.

## Benchmarks

Formal design-task benchmarks coming soon. Model speeds may be slower than expected due to the system prompt.

## Notes

* No architectural changes to base model
* Fully compatible with Qwen3.5 tooling
* Optimized for design and creative workflows
* Works well with Gemini-style prompt pipelines
* 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)