Pinned Loading

1. q38rocm q38rocm Public

   Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

   Python 221 12

2. halofpx halofpx Public

   High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silicon-t…

   Python 69 3

3. ds4fa ds4fa Public

   DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2

   C 14 1

4. npuhalo-speech npuhalo-speech Public

   NPU-accelerated speech transcription & speaker diarization on AMD Strix Halo: Whisper-v3-turbo on XDNA 2 + pyannote, OpenAI-compatible API and browser studio

   Python 9

5. npuhalo npuhalo Public

   Unlocking the power of the Halo NPU: NPU + iGPU live verification, compression, and routing research on AMD Strix Halo

   Python 2 2

6. Stabolut/mobile Stabolut/mobile Public

   Mobile app empowering users to transfer USB tokens securely between wallets with gasless transactions. Features include built-in secure wallet functionality and seamless integration with USB Token …

   JavaScript