llamaperf

Qwen3.8 27B sabi-noema

on M5 Ultra 96GB · Inco Splash

Tone: mixedApple hardware
Nov 7, 2026
Throughput
119.0 t/s gen
Quant
6bit
System RAM
96 GB

Use cases

codingagentic

Summary

User compares a 6-bit fine-tune of Qwen3.8 27B called sabi-noema against Qwen3.8 Flash-Next on an M5 Ultra Mac Studio 96GB, with MTP enabled for both. The 27B fine-tune reached 119 tok/s against 90 tok/s for Flash-Next, and the user notes better performance on Splash for the 27B. Flash-Next used 2.5x the memory with N-gram offload, 73GB peak versus 29GB peak. The user found the 27B better at coding tests and prose, while Flash-Next did better on broad knowledge.

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.

Models most run on the M5 Ultra 96GB

Bars are medians on one scale, 0 to 15.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the M5 Ultra 96GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →