Benchmark result
ornith15-heretic-mini on NVIDIA RTX A2000 12GB +1 more — 72.2 tok/s
Measured with llama.cpp manual on October 15, 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
2nd fastest of 2 runs of this model on NVIDIA RTX A2000 12GB +1 more · Multi-GPU · median 72.9 tok/s.
sort
- 173.6tok/s77.7llama.cpp
- 272.2tok/s74.5llama.cppthis run
Reproduce this run
toolllama.cpp manual
modelornith15-heretic-mini
context65,536
thinkingoff
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ornith15-heretic-mini" --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.