Benchmark result
nvidia/nemotron-3-nano-4b on NVIDIA GeForce GTX 1050 — 4.9 tok/s
Measured with LM Studio on October 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
2nd fastest of 3 runs of this model on NVIDIA GeForce GTX 1050 · median 4.9 tok/s.
sort
- 15.0tok/s39.6LM Studio · Q4_K_M
- 24.9tok/s36.4LM Studio · Q4_K_Mthis run
- 34.8tok/s49.7LM Studio · Q4_K_M
nvidia/nemotron-3-nano-4b on other hardware
Reproduce this run
toolLM Studio
modelnvidia/nemotron-3-nano-4b (Q4_K_M)
context8,192
thinkingoff
clientv0.4.92+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "nvidia/nemotron-3-nano-4b" --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.