Benchmark result
qwen3.6-35b-a3b-ud-q4_k_m on 2× NVIDIA GeForce RTX 5060 — 128.2 tok/s
Measured with llama.cpp PolyStrata 0.1.45 on November 21, 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 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 128.7 tok/s.
- 1129.2tok/s80.6PolyStrata · Q4_K_M
- 2128.2tok/s81.3llama.cpp · Q4_K_Mthis run
qwen3.6-35b-a3b-ud-q4_k_m on other hardware
Reproduce this run
Set those in llama.cpp, then:
llm-benchmark benchmark --model "qwen3.6-35b-a3b-ud-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.