Benchmark result
OrcaCyber-Nano-1.0-AI-Defense-Mix-13G on AMD Radeon RX 7800 XT — 44.4 tok/s
Measured with llama.cpp k8 vTurbo4 manual on October 19, 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 2 runs of this model on AMD Radeon RX 7800 XT · median 43.5 tok/s.
sort
- 144.4tok/s83.7llama.cpp k8 vTurbo4this run
- 242.7tok/s81.6llama.cpp k4 v4
Reproduce this run
toolllama.cpp k8 vTurbo4 manual
modelOrcaCyber-Nano-1.0-AI-Defense-Mix-13G
context65,536
thinkingon
clientv0.4.92+102
Set those in llama.cpp k8 vTurbo4, then:
llm-benchmark benchmark --model "OrcaCyber-Nano-1.0-AI-Defense-Mix-13G" --tool "llama.cpp k8 vTurbo4"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.