Benchmark result
qwen/qwen3-4b-2507 on NVIDIA GeForce RTX 2050 — 34.8 tok/s
Measured with LM Studio on November 21, 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
3rd fastest of 4 runs of this model on NVIDIA GeForce RTX 2050 · median 34.9 tok/s.
sort
- 135.3tok/s69.6LM Studio · Q4_K_M
- 235.1tok/s74.2LM Studio · Q4_K_M
- 334.8tok/s68.1LM Studio · Q4_K_Mthis run
- 434.6tok/s68.5LM Studio · Q4_K_M
Reproduce this run
toolLM Studio
modelqwen/qwen3-4b-2507 (Q4_K_M)
context65,536
clientv0.4.99+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3-4b-2507" --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.