Speech recognition models running on the Ryzen AI NPU with Windows ML.
🔄 In a Training Loop
Von
Harsha001
AI & ML interests
ROCmFPX GGUF quants for AMD GPUs and Strix Halo. Every file is scored by KLD against BF16. Speech models ported to the AMD XDNA2 NPU.
Recent Activity
new activity about 20 hours ago
Harsha001/Nanbeige4.3-33B-ROCmFPX:DeepSeek V4.1 Flash 1017 (GSQ-RCO) updated a model about 23 hours ago
Harsha001/humanizer-12b-ROCmFPX published a model about 23 hours ago
Harsha001/humanizer-12b-ROCmFPXOrganizations
None yet
models 19
Harsha001/humanizer-12b-ROCmFPX
Text Generation • 12B • Updated
Harsha001/Nanbeige4.3-33B-ROCmFPX
Text Generation • 33B • Updated • 129 • 3
Harsha001/Qwen3.8-27B-Uncensored-ROCmFPX
Image-Text-to-Text • 27B • Updated • 243 • 1
Harsha001/flint-ROCmFPX
Text Generation • 40B • Updated • 396 • 1
Harsha001/Kolibri-1-ROCmFPX
Text Generation • 78B • Updated • 156
Harsha001/elephant-1-ROCmFPX
Text Classification • 9B • Updated • 207
Harsha001/mammoth-1-ROCmFPX
Text Classification • 27B • Updated • 161
Harsha001/Sage-A1.5-ROCmFPX
Text Generation • 36B • Updated • 308
Harsha001/Drama-3-ROCmFPX-GGUF
Text-to-Speech • 36B • Updated • 425
Harsha001/MiniCPM-V-4.7-35B-A3B-ROCmFPX
Text Generation • 35B • Updated • 715
datasets 0
None public yet