Benchmark result
huihui-qwen3.8-27b-abliterated-oq5e-mtp on Apple M5 Max — 29.5 tok/s
Measured with LM Studio on September 8, 2026.
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 Max · median 30.9 tok/s.
sort
- 132.2tok/s2.9LM Studio
- 229.5tok/s0.2LM Studiothis run
Reproduce this run
toolLM Studio
modelhuihui-qwen3.8-27b-abliterated-oq5e-mtp
context65,536
clientv0.4.55+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "huihui-qwen3.8-27b-abliterated-oq5e-mtp" --tool "LM Studio"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.