Qwen3.8 125B (6B active) Flash-Next
on Intel Arc B580 12GB · Strata · 262,144 ctx
Use cases
agenticvisionlong-context
Summary
User reports Qwen3.8-Flash-Next at 21.0 tok/s on an Intel Arc B580 12GB.
Setup is Strata v0.1.40.4 with IQ2_XS quantization and INT8 KV cache, 256K context, 2808 resident expert slots, speculative decoding with MTP.
Long-context stress test at 74,213 prompt tokens sustained 17.8 tok/s for 237.7 seconds. User compares to llama.cpp/Ollama offload at 1.5-3.0 tok/s and previous Strata version at 17.1 tok/s.