llamaperf

Qwen3.8 27B

on M5 Ultra 96GB · Ollama · 6,600 ctx

Tone: mixedApple hardware
Nov 1, 2026
Throughput
52.9 t/s gen · 1168.0 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
MXFP8 (MLX)
KV cache
q8_0
System RAM
96 GB

Use cases

codingtool-useagentic

Summary

User reports Qwen3.8-27B at 52.9 t/s decode on a 6.6K prompt and 1,168 t/s prompt eval on a Mac Studio M5 Ultra 96GB (64-core GPU), compared against oMLX at 23.3 t/s cold and 29.7 t/s warm on the same model. Setup is Ollama 0.40.13 with the MLX runner, MXFP8 weights, q8_0 KV cache and a 131072 context; the wired memory limit was raised to 86GB. Other Ollama short-prompt speeds: gpt-oss:120b 95 to 102 t/s, qwen3-coder-next 107 t/s, qwen3.6:35b-a3b 246 t/s, llama4:scout 49 t/s. On long prompts gpt-oss prefill was 2,588 t/s at ~15K and 1,996 t/s at ~60K, Coder-Next 3,382 and 2,687 t/s, Qwen3.8 1,376 and 1,243 t/s. The user expected oMLX to win and it did not, and notes Qwen3.8's thinking volume (10,339 tokens, 161 s) as a real cost.

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 27B at 4-bit by hardware

Bars are medians on one scale, 0 to 94.0 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 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 →