llamaperf

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

on M5 Pro 24GB · MoEShift · 6,060 ctx

Tone: positiveApple hardware
Nov 9, 2026
Throughput
14.7 t/s gen · 374.1 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
IQ3_XXS (GGUF)
System RAM
24 GB

Use cases

agentic

Summary

User benchmarks Qwen3.8-Flash-Next 125B at 14.69 tok/s decode on an M5 Pro 24GB, with 374.15 tok/s prefill on a 6,060-token prompt. Setup is the MoEShift backend with an IQ3_XXS quant (76GB on disk) and SSD offloading, peak process memory 8.5GB. Medians of 3 runs with prompt caching disabled. On the same setup an M4 Pro 24GB reached 9.84 tok/s short-prompt decode, 199.09 tok/s prefill and 9.57 tok/s long-prompt decode; long-prompt inference took 55.1s on the M5 Pro versus 83.9s on the M4 Pro.

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 M5 Pro 24GB

Bars are medians on one scale, 0 to 125.8 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the M5 Pro 24GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →