Benchmark result
mlx-community/Qwen3.8-27B-4bit on Apple M5 Ultra — 121.3 tok/s
Measured with splash manual on November 5, 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.
How this run compares
2nd fastest of 2 runs of this model on Apple M5 Ultra · median 128.0 tok/s.
sort
- 1134.8tok/s73.8splash
- 2121.3tok/s89.4splashthis run
mlx-community/Qwen3.8-27B-4bit on other hardware
Reproduce this run
toolsplash manual
modelmlx-community/Qwen3.8-27B-4bit
context65,536
thinkingon
clientv0.4.98+102
Set those in splash, then:
llm-benchmark benchmark --model "mlx-community/Qwen3.8-27B-4bit" --tool "splash"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.