llamaperf

Qwen3.8 27B

on Unknown GPU · oMLX

Tone: positive
Nov 1, 2026
Throughput
75.0 t/s gen
Quant
Q6

Use cases

agentictool-use

Summary

User reports Qwen3.8 27B running at 75 tok/s at Q6 in oMLX, with browser access configured via MCP. The post names no GPU or other hardware, and no context length or KV cache setting. User says the speed is enough that they have stopped using a private Cursor subscription, and that the model also got past a reCAPTCHA during a web fetch.

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.

Every Qwen3.8 report →