Benchmark result
ling-oq4e on Apple M1 — 47.6 tok/s
Measured with LM Studio on September 12, 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
3rd fastest of 4 runs of this model on Apple M1 · median 47.6 tok/s.
sort
- 147.9tok/s49.6LM Studio
- 247.7tok/s53.0LM Studio
- 347.6tok/s40.8LM Studiothis run
- 447.3tok/s41.1LM Studio
Reproduce this run
toolLM Studio
modelling-oq4e
context8,192
clientv0.4.59+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "ling-oq4e" --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.