Qwen3.8 125B (6B active) Flash-Next
on AMD Strix Halo 128GB · llama.cpp · 95,600 ctx
Summary
User reports Qwen3.8-Flash-Next (125B-A6B) at 41.0 tok/s decode on short context and 1183 t/s prefill on a 95.6K-token prompt, on a Ryzen AI Max+ 395 with 128 GB (Strix Halo).
Setup is a patched llama.cpp HIP runtime with Unsloth UD-IQ4_XS weights (93.7 GB), MTP speculative decoding with three draft tokens, and optional Q8_0 K/V cache; the GPU carve is set to 96 GB.
Decode falls to 32.6 tok/s at 86K context; three and four concurrent conversations reach 55.7 and 60.4 tok/s summed. Prefill is given as a three-run range of 1167-1191 t/s.