Benchmark result
Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL on Tesla P100-PCIE-16GB — 38.8 tok/s
Measured with llama.cpp b1-5266f24 on September 21, 2026.
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 3 runs of this model on Tesla P100-PCIE-16GB · median 38.4 tok/s.
sort
- 138.8tok/s60.8llama.cpp · Q4_Kthis run
- 238.4tok/s55.6llama.cpp · Q4_K
- 338.3tok/s73.8llama.cpp · Q4_K
Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL on other hardware
Reproduce this run
toolllama.cpp b1-5266f24
modelTiel-Coder-35B-A3B-MTP-UD-Q4_K_XL (Q4_K)
context65,536
thinkingoff
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.71+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-MTP-UD-Q4_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.