Benchmark result
tensorfold-qwen38-27b on Apple M4 Pro — 25.0 tok/s
Measured with TensorFold manual on October 14, 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 M4 Pro · median 25.0 tok/s.
sort
- 125.1tok/s84.7TensorFold
- 225.0tok/s84.9TensorFoldthis run
Reproduce this run
toolTensorFold manual
modeltensorfold-qwen38-27b
context16,384
thinkingon
clientv0.4.93+102
Set those in TensorFold, then:
llm-benchmark benchmark --model "tensorfold-qwen38-27b" --tool "TensorFold"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.