Downloads · 30 days
374
12% of all-time downloads
Qwen3.8-27B-ROCmFPX-GGUF
hugobugo34/Qwen3.8-27B-ROCmFPX-GGUF
Qwen3.8-27B-ROCmFPX-GGUF is a machine learning model from hugobugo34. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ROCmFPX GGUF quantization of Qwen/Qwen3.8-27B
All-time downloads
3.2K
Public
Repo size
57.2 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf48 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 14, 2026
- Updated
- Aug 16, 2026
- SHA
- 83bec8fe
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-ROCmFPX-GGUF
ROCmFPX GGUF quantization of Qwen/Qwen3.8-27B
AMD focused model weight formats. Tested on AMD 7900 XTX
Requires ROCmFPX llama.cpp build to run. See link below
Quantizations available
| File | ROCmFPX preset | Size |
|---|---|---|
Qwen3.8-27B-ROCmFP4.gguf | Q4_0_ROCMFP4 | 17.7 GB |
Qwen3.8-27B-ROCMFP4-COHERENT.gguf | Q4_0_ROCMFP4_COHERENT | 15.7 GB |
Qwen3.8-27B-ROCmFP4-FAST.gguf | Q4_0_ROCMFP4_FAST | 14.6 GB |
Related links
- Qwen3.8-27B (Qwen Repo)
- ROCmFPX (Github Repo)
- License
- apache-2.0
- Created
- Aug 14, 2026
- Updated
- Aug 16, 2026