llamaperf

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

on M1 Max 64GB · Strata

Tone: positiveApple hardware
Nov 7, 2026
Throughput
24.0 t/s gen
System RAM
64 GB

Summary

User reports Qwen3.8 Flash-Next running at 24 tok/s on an M1 Max 64GB MacBook Pro. Setup is Strata, with larger models offloaded to SSD via a MoEShift-style offloading technique. User says the model does phenomenal work and recommends Strata, hoping the offloading approach gets more research.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.8 125B · 6B active at 4-bit by hardware

Bars are medians on one scale, 0 to 232.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the M1 Max 64GB

Bars are medians on one scale, 0 to 56.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the M1 Max 64GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →