Benchmark result
huihui-qwen3.6-35b-a3b-abliterated-q5_k on NVIDIA GeForce RTX 4070 — 134.7 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
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 4070 · median 136.4 tok/s.
sort
- 1138.1tok/s66.8llama.cpp · Q5_K
- 2134.7tok/s81.3llama.cpp · Q5_Kthis run
Reproduce this run
toolllama.cpp PolyStrata 0.1.45
modelhuihui-qwen3.6-35b-a3b-abliterated-q5_k (Q5_K)
context32,768
think limitnone
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "huihui-qwen3.6-35b-a3b-abliterated-q5_k" --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.