Benchmark result
nvidia-nemotron-3.5-lightning-30b-a3b on Apple M5 Max — 111.5 tok/s
Measured with LM Studio on October 11, 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
nvidia-nemotron-3.5-lightning-30b-a3b on other hardware
Reproduce this run
toolLM Studio
modelnvidia-nemotron-3.5-lightning-30b-a3b (Q4_K_M)
context65,536
thinkingon
clientv0.4.85+101
Set those in LM Studio, then:
llm-benchmark benchmark --model "nvidia-nemotron-3.5-lightning-30b-a3b" --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.