Qwen3.8 27B

on M4 Max 36GB · Inco Splash · 256,000 ctx

Oct 16, 2026

Throughput

15.0 t/s gen · 100.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

System RAM

36 GB

Summary

User reports Qwen3.8 27B at 15 t/s generation and about 100 t/s prefill on an M4 Max 36GB MacBook, running a 256K-token prompt. Setup is Inco Splash; no quant or KV cache format stated. User questions how the run fits in 36GB of RAM without significant swap.

View source ↗