Benchmark result
cyber-tiel-coder-35b-a3b-mtp-ud-q6_k_xl on NVIDIA GeForce RTX 4070 — 93.0 tok/s
Measured with llama.cpp PolyStrata 0.1.45 on November 14, 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 92.4 tok/s.
- 193.0tok/s85.2llama.cpp · Q6_Kthis run
- 291.7tok/s82.8llama.cpp · Q6_K
cyber-tiel-coder-35b-a3b-mtp-ud-q6_k_xl on other hardware
Reproduce this run
Set those in llama.cpp, then:
llm-benchmark benchmark --model "cyber-tiel-coder-35b-a3b-mtp-ud-q6_k_xl" --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.