Benchmark result
qwen/qwen3-1.7b on NVIDIA GeForce RTX 2050 — 56.0 tok/s
Measured with LM Studio on October 30, 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
4th fastest of 4 runs of this model on NVIDIA GeForce RTX 2050 · median 56.5 tok/s.
sort
- 160.9tok/s49.9LM Studio · Q6_K
- 257.0tok/s46.8LM Studio · Q6_K
- 356.0tok/s47.1LM Studio · Q6_K
- 456.0tok/s47.7LM Studio · Q6_Kthis run
qwen/qwen3-1.7b on other hardware
Reproduce this run
toolLM Studio
modelqwen/qwen3-1.7b (Q6_K)
context16,384
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3-1.7b" --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.