Benchmark result
iq3_s on NVIDIA GeForce RTX 3090 — 47.8 tok/s
Measured with Strata Strata (manual) on November 6, 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
12th fastest of 16 runs of this model on NVIDIA GeForce RTX 3090 · median 53.5 tok/s.
sort
- 1101.5tok/s89.1Strata
- 299.8tok/s87.5Strata
- 399.5tok/s75.1Strata
- 495.7tok/s65.8Strata
- 556.9tok/s84.3Strata
- 656.6tok/s86.4Strata
- 755.5tok/s89.4Strata
- 854.0tok/s89.9Strata
- 952.9tok/s86.1Strata
- 1051.6tok/s84.3Strata
- 1151.1tok/s82.2Strata
- 1247.8tok/s82.3Stratathis run
- 1343.1tok/s82.0Strata
- 1427.8tok/s85.1Strata
- 1525.5tok/s86.8Strata
- 1624.3tok/s86.4Strata
Reproduce this run
toolStrata Strata (manual)
modeliq3_s
context131,072
thinkingon
think limitnone
clientv0.4.98+102
Set those in Strata, then:
llm-benchmark benchmark --model "iq3_s" --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.