Benchmark result
tiel-coder-35b on NVIDIA RTX A2000 12GB +1 more — 75.7 tok/s
Measured with llama.cpp manual on October 16, 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 3 runs of this model on NVIDIA RTX A2000 12GB +1 more · Multi-GPU · median 75.7 tok/s.
sort
- 178.6tok/s70.6llama.cpp
- 275.7tok/s74.6llama.cppthis run
- 373.5tok/s83.4llama.cpp
tiel-coder-35b on other hardware
Reproduce this run
toolllama.cpp manual
modeltiel-coder-35b
context65,536
thinkingoff
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "tiel-coder-35b" --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.