Benchmark result
nemotron-3.5-bolt on AMD Radeon AI PRO R9700 — 116.6 tok/s
Measured with Strata Strata strata-nemo on October 23, 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 AMD Radeon AI PRO R9700 · median 105.7 tok/s.
sort
- 1116.6tok/s67.8Stratathis run
- 294.9tok/s76.5Strata
Reproduce this run
toolStrata Strata strata-nemo
modelnemotron-3.5-bolt
context8,192
thinkingoff
samplingtemperature 1 · top_p 0.95
clientv0.4.97+102
Set those in Strata, then:
llm-benchmark benchmark --model "nemotron-3.5-bolt" --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.