Benchmark result
ornith-1.5-35b-a3b-crack-q4_k_m on NVIDIA GeForce RTX 4070 — 106.5 tok/s
Measured with llama.cpp PolyStrata 0.1.45 on November 13, 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 4070 · median 104.0 tok/s.
sort
- 1106.5tok/s65.3llama.cpp · Q4_K_Mthis run
- 2101.6tok/s81.2llama.cpp · Q4_K_M
Reproduce this run
toolllama.cpp PolyStrata 0.1.45
modelornith-1.5-35b-a3b-crack-q4_k_m (Q4_K_M)
context65,536
think limitnone
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ornith-1.5-35b-a3b-crack-q4_k_m" --tool "llama.cpp"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.