Benchmark result
luciole-1b-instruct-1.1 on NVIDIA GeForce RTX 2050 — 62.3 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
2nd fastest of 3 runs of this model on NVIDIA GeForce RTX 2050 · median 62.3 tok/s.
sort
- 163.1tok/s20.5LM Studio · Q8_0
- 262.3tok/s20.4LM Studio · Q8_0this run
- 359.9tok/s23.8LM Studio · Q8_0
Reproduce this run
toolLM Studio
modelluciole-1b-instruct-1.1 (Q8_0)
context8,192
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "luciole-1b-instruct-1.1" --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.