Qwen3.8 27B
on Unknown GPU · oMLX
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
- NVIDIA RTX 509032 GB80.0 t/s · 7 runs
- 67.0 t/s · one run
- NVIDIA RTX 5070 Ti16 GB54.7 t/s · one run
- 50.0 t/s · one run
- NVIDIA RTX 409024 GB40.0 t/s · 3 runs
- AMD RX 7900 XTX24 GB40.0 t/s · 7 runs
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.