Benchmark result
ministral-3b-instruct on NVIDIA GeForce RTX 2050 — 50.6 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 5 runs of this model on NVIDIA GeForce RTX 2050 · median 49.3 tok/s.
sort
- 150.6tok/s2.3LM Studio · Q4_K_Mthis run
- 249.7tok/s1.7LM Studio · Q4_K_M
- 349.3tok/s3.1LM Studio · Q4_K_M
- 414.0tok/s2.2LM Studio · Q4_K_M
- 512.2tok/s1.4LM Studio · Q4_K_M
Reproduce this run
toolLM Studio
modelministral-3b-instruct (Q4_K_M)
context16,384
clientv0.4.96+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "ministral-3b-instruct" --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.