Benchmark result
smollm3-3b@q6_k on NVIDIA GeForce RTX 2050 — 33.5 tok/s
Measured with LM Studio on October 25, 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
1st fastest of 3 runs of this model on NVIDIA GeForce RTX 2050 · median 33.4 tok/s.
sort
- 133.5tok/s37.6LM Studio · Q6_Kthis run
- 233.4tok/s49.7LM Studio · Q6_K
- 332.1tok/s53.0LM Studio · Q6_K
Reproduce this run
toolLM Studio
modelsmollm3-3b@q6_k (Q6_K)
context32,768
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "smollm3-3b@q6_k" --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.