Qwen3.8 27B
on M3 Ultra 96GB · 100,000 ctx
Summary
User asks what throughput to expect from Qwen 3.8 27B on an M3 Ultra 96GB at 100k context, and whether it would be twice as fast as their current setup.
Their current two-eGPU setup runs the Q4_K_M model at 23-30 tk/s, which they call usable but slow.
No M3 Ultra figures were measured; the post is a question, not a benchmark.