Qwen3.8-27B-ROCmFPX-GGUF – AI Model by hugobugo34 | AlphaNeural AI

You can deploy this model and start earning money today!

hugobugo34/
Qwen3.8-27B-ROCmFPX-GGUF

like

0

Qwen/Qwen3.8-27B

endpoints_compatible

Views

No views yet

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)