Qwendean-4B GGUF
Qwendean is a fine-tuned Qwen3-4B model built specifically for generating UI components. Give it a plain-English description of a UI section and it outputs clean, copy-paste-ready TypeScript/React code using ShadCN UI and Tailwind CSS.
Available Files
| File | Quant | Size | Recommended For |
|---|---|---|---|
Qwendean-4B.Q4_K_M.gguf |
Q4_K_M | 2.5 GB | Most users |
Qwendean-4B.Q5_K_M.gguf |
Q5_K_M | 2.89 GB | Better quality (default) |
Qwendean-4B.Q8_0.gguf |
Q8_0 | 4.28 GB | Maximum quality |
Usage
Ollama
ollama run hf.co/iamdyeus/qwendean-4b-GGUF
llama.cpp
llama-cli -hf iamdyeus/qwendean-4b-GGUF --jinja
LM Studio
Search iamdyeus/qwendean-4b-GGUF in the model browser.
Prompting
Give it direct, specific UI descriptions:
- "Build a hero section with a headline, subtitle, and two CTA buttons"
- "Create a sidebar navigation with icons and collapsible sections"
It outputs TSX only — no explanations, no conversation.
Links
- 🤗 Main model repo: iamdyeus/qwendean-4b
- Downloads last month
- 194
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for iamdyeus/qwendean-4b-GGUF
Base model
Qwen/Qwen3-4B-Base Finetuned
Qwen/Qwen3-4B Finetuned
unsloth/Qwen3-4B Finetuned
iamdyeus/qwendean-4b