Benchmark result
Qwen3-1.7B-GGUF on NVIDIA GeForce RTX 2050 — 72.0 tok/s
Measured with Lemonade manual on November 15, 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
2nd fastest of 3 runs of this model on NVIDIA GeForce RTX 2050 · median 72.0 tok/s.
sort
- 172.7tok/s25.5Lemonade
- 272.0tok/s44.4Lemonadethis run
- 371.8tok/s42.0Lemonade
Reproduce this run
toolLemonade manual
modelQwen3-1.7B-GGUF
context32,768
clientv0.4.99+102
Set those in Lemonade, then:
llm-benchmark benchmark --model "Qwen3-1.7B-GGUF" --tool "Lemonade"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.