Qwen3.8
on AMD Strix Halo 128GB · Atlas Inference · 65,536 ctx
Use cases
agentictool-use
Summary
User reports Qwen3.8 NVFP4 at 20.6 t/s on an AMD Strix Halo 128GB, with 17.3 t/s on Windows.
Setup is Atlas Inference running natively on HIP with custom DP4A math on gfx1151, using K=4 draft speculative decoding and a 65k agentic context window. The engine is the sole cross-architecture submission for MLPerf Inference v6.1 Edge Agentic LLM SingleStream, scoring 87.76 normalized BFCL and 84 on HA-20.
Median TPOT is 47.3 ms and median TTFT is 2.7s across 65k context windows.