Benchmark result
iq3_xxs on NVIDIA GeForce RTX 3090 — 119.9 tok/s
Measured with Strata Strata (manual) on November 6, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 3090 · median 117.4 tok/s.
sort
- 1119.9tok/s80.3Stratathis run
- 2114.8tok/s84.2Strata
Reproduce this run
toolStrata Strata (manual)
modeliq3_xxs
context131,072
think limitnone
clientv0.4.99+102
Set those in Strata, then:
llm-benchmark benchmark --model "iq3_xxs" --tool "Strata"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.