Qwen3.8 125B (6B active) Flash-Next
on 4× 4x BC-250 · llama.cpp · 100,096 ctx
Summary
User reports running Qwen3.8 Flash-Next IQ3_XXS at 59.4-65.2 tok/s prompt and 66.6-68.3 tok/s generation on 4 BC-250 boards with 100K context.
Setup is llama.cpp with Vulkan and RPC over 2.5gb ethernet, using speculative decoding with the model's own MTP draft head. The cluster also runs two instances of Qwen3.6 35B A3B at 145 tok/s generation and 450 tok/s prompt with 256K context.
Power draw is 600-700 W for Flash-Next and 800-900 W for the two 35B instances. Boards cost under $100 each.