Qwen3.8 125B (6B active) Flash-Next
on M1 Max 64GB · Strata
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
- 129.2 t/s · one run
- 105.5 t/s · 6 runs
- 57.2 t/s · 2 runs
- 55.0 t/s · one run
- 36.7 t/s · one run
- NVIDIA DGX Spark128 GB29.8 t/s · 2 runs
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
- 56.0 t/s · one run
- Qwen3.8 27B4-bit16.9 t/s · one run
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 →