Benchmark result
Ornith-1.5-35B-Uncensored-YMQ-S on 2× NVIDIA GeForce RTX 5060 — 78.9 tok/s
Measured with llama.cpp b11549-aa94f2086 on October 10, 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.
Reproduce this run
toolllama.cpp b11549-aa94f2086
modelOrnith-1.5-35B-Uncensored-YMQ-S
context131,072
thinkingon
think limit32,768 tokens
samplingtemperature 0.6000000238418579 · top_p 0.800000011920929 · top_k 20 · min_p 0.10000000149011612 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.91+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Ornith-1.5-35B-Uncensored-YMQ-S" --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.