Benchmark result
thinkingmachines/inkling-2-mini on Apple M5 Max — 41.2 tok/s
Measured with LM Studio on November 22, 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 3 runs of this model on Apple M5 Max · median 41.2 tok/s.
sort
- 141.3tok/s80.2LM Studio · Q4_K_M
- 241.2tok/s87.4LM Studio · Q4_K_Mthis run
- 341.2tok/s85.6LM Studio · Q4_K_M
thinkingmachines/inkling-2-mini on other hardware
Reproduce this run
toolLM Studio
modelthinkingmachines/inkling-2-mini (Q4_K_M)
context131,072
clientv0.4.99+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "thinkingmachines/inkling-2-mini" --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.