Qwen3.8 125B (6B active) Flash-Next

Sep 7, 2026

Throughput

10.0 t/s gen · 165.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

System RAM

64 GB

Summary

User reports a run on a 64GB M1 Max. No drafter was used. User mentions n-gram and stripping embeddings as potential optimizations.

View source ↗