Benchmark result
ornith-1.5-35b-a3b-apex-i-quality on NVIDIA GeForce RTX 3070 Ti — 42.7 tok/s
Measured with Polystrata manual on November 11, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 3070 Ti · median 42.4 tok/s.
sort
- 142.7tok/s86.5Polystratathis run
- 242.2tok/s88.0Polystrata
ornith-1.5-35b-a3b-apex-i-quality on other hardware
Reproduce this run
toolPolystrata manual
modelornith-1.5-35b-a3b-apex-i-quality
context131,072
clientv0.4.99+102
Set those in Polystrata, then:
llm-benchmark benchmark --model "ornith-1.5-35b-a3b-apex-i-quality" --tool "Polystrata"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.