Benchmark result
True2456--Qwen3.8-27B-AWQ-5.0bpw on Apple M5 Pro — 27.2 tok/s
Measured with oMLX 0.31.3 on August 18, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
Reproduce this run
tooloMLX 0.31.3
modelTrue2456--Qwen3.8-27B-AWQ-5.0bpw
context8,192
clientv0.4.36+97
Set those in oMLX, then:
llm-benchmark benchmark --model "True2456--Qwen3.8-27B-AWQ-5.0bpw" --tool "oMLX"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.