Benchmark result
swift-iq2_xs on NVIDIA GeForce RTX 4070 — 92.9 tok/s
Measured with Strata Strata (manual) on November 2, 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 4070 · median 91.5 tok/s.
sort
- 192.9tok/s87.3Stratathis run
- 290.1tok/s88.5Strata
Reproduce this run
toolStrata Strata (manual)
modelswift-iq2_xs
context32,768
thinkingon
think limitnone
clientv0.4.98+102
Set those in Strata, then:
llm-benchmark benchmark --model "swift-iq2_xs" --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.