Qwen3.8 125B (6B active) Flash-Next
on M3 Ultra 96GB · oMLX · 200,000 ctx
Use cases
agenticcoding
Summary
User reports Flash-Next running through oMLX plus Splash on a Mac Studio M3 Ultra 96GB, used mainly for agentic coding with Pi.
Generation is given as 70–100 tokens/s and prefill as 900–1,000 tokens/s, both sustained up to 200K tokens of context with no noticeable degradation.
No quant, KV cache format or single measured figure is stated.