Benchmark result
qwen2.5-1.5b-instruct on NVIDIA GeForce RTX 2050 — 69.5 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
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 2050 · median 69.7 tok/s.
sort
- 170.0tok/s25.8LM Studio · Q6_K
- 269.5tok/s25.8LM Studio · Q6_Kthis run
qwen2.5-1.5b-instruct on other hardware
Reproduce this run
toolLM Studio
modelqwen2.5-1.5b-instruct (Q6_K)
context16,384
clientv0.4.96+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen2.5-1.5b-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.