Benchmark result
recursivesi/flint on Apple M5 Max — 108.7 tok/s
Measured with LM Studio on October 30, 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 4 runs of this model on Apple M5 Max · median 107.6 tok/s.
sort
- 1109.3tok/s68.0LM Studio · Q4_K_M
- 2108.7tok/s73.8LM Studio · Q4_K_Mthis run
- 3106.6tok/s77.9LM Studio · Q4_K_M
- 4105.1tok/s77.4LM Studio · Q4_K_M
Reproduce this run
toolLM Studio
modelrecursivesi/flint (Q4_K_M)
context131,072
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "recursivesi/flint" --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.