Harsha001/Qwen3.8-27B-Uncensored-ROCmFPX
Image-Text-to-Text • 27B • Updated • 390 • 1
ROCmFPX language models
Low-bit GGUF files for AMD GPUs (Vulkan and HIP) with the ROCmFPX llama.cpp fork. Every file is measured against BF16.
-
-
Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX
Text Generation • 8B • Updated • 307 -
Harsha001/flint-ROCmFPX
Text Generation • 40B • Updated • 416 • 1 -
Harsha001/Carbon-X-ROCmFPX
Text Generation • 15B • Updated • 251 • 1 -
Harsha001/Spark-X2.6-4B-ROCmFPX
Text Generation • 4B • Updated • 275 • 1 -
Harsha001/Sage-A1.5-ROCmFPX
Text Generation • 36B • Updated • 420 -
Harsha001/Kolibri-1-ROCmFPX
Text Generation • 78B • Updated • 182 -
Harsha001/Ornith-1.5-122B-ROCmFPX
Text Generation • 122B • Updated • 275 -
Harsha001/MiniCPM-V-4.7-35B-A3B-ROCmFPX
Text Generation • 35B • Updated • 967 -
Harsha001/Drama-3-ROCmFPX-GGUF
Text-to-Speech • 36B • Updated • 474 • 1 -
Harsha001/mammoth-1-ROCmFPX
Text Classification • 27B • Updated • 166 -
Harsha001/elephant-1-ROCmFPX
Text Classification • 9B • Updated • 229