Benchmark result
Qwen3.5-2B-GGUF-Q8_0 on NVIDIA GeForce RTX 2050 — 38.3 tok/s
Measured with Lemonade manual on November 20, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 2050 · median 38.2 tok/s.
sort
- 138.3tok/s43.3Lemonade · Q8_0this run
- 238.0tok/s34.4Lemonade · Q8_0
Reproduce this run
toolLemonade manual
modelQwen3.5-2B-GGUF-Q8_0 (Q8_0)
context16,384
thinkingoff
clientv0.4.99+102
Set those in Lemonade, then:
llm-benchmark benchmark --model "Qwen3.5-2B-GGUF-Q8_0" --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.