Benchmark result
google/gemma-3-4b on NVIDIA GeForce RTX 2050 — 24.6 tok/s
Measured with LM Studio on October 16, 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 2 runs of this model on NVIDIA GeForce RTX 2050 · median 24.4 tok/s.
sort
- 124.6tok/s46.3LM Studio · Q3_K_Lthis run
- 224.2tok/s42.0LM Studio · Q3_K_L
Reproduce this run
toolLM Studio
modelgoogle/gemma-3-4b (Q3_K_L)
context16,384
clientv0.4.96+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "google/gemma-3-4b" --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.