Downloads · 30 days
0
Phi-4-mini-reasoning-webgpu
LJTSG/Phi-4-mini-reasoning-webgpu
Phi-4-mini-reasoning-webgpu is a text generation model from LJTSG. Use it when you need the model to write or continue text. The card lists the license as mit.
First WebGPU package for Microsoft's Phi-4-mini-reasoning model.
Access
Public
Updated Jun 3, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.html5 KB · 52%
At a glance
- Task
- Text Generation
- License
- mit
- Access
- Public
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026
- SHA
- 2c6ab372
Try a prompt
Base models
Model card
From the Hugging Face model README
Phi-4-mini-reasoning on WebGPU
First WebGPU package for Microsoft's Phi-4-mini-reasoning model.
The reasoning variant (not instruct) trained on DeepSeek-R1 chain-of-thought distillation. 3.8B params, 2.4 GB Q4_K_M. Runs entirely in browser via WebGPU + wllama.
Quick Start
- Download Q4_K_M GGUF from bartowski
- Place in model_splits/ (single file, no splitting needed)
- node serve.js (port 8190)
- Open http://localhost:8190 in Chrome
Hardware
Tested on GMKTEC EVO-X2 (AMD Strix Halo). Works on any WebGPU-capable device with 3+ GB available memory.
Credits
Built by Joshua (LJTSG) and Claude. Co-Authored-By: Claude [email protected]
- Task
- Text Generation
- License
- mit
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026