Benchmark result
Ornith-1.5-35B-A3B-GSQ-RCO-3bit-ASCII-Condensed on AMD Radeon RX 7800 XT — 107.2 tok/s
Measured with llama.cpp k8 v4 -1 budget manual on October 9, 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 106.2 tok/s.
sort
- 1107.2tok/s64.6llama.cpp k8 v4 -1 budgetthis run
- 2105.3tok/s73.7llama.cpp
Reproduce this run
toolllama.cpp k8 v4 -1 budget manual
modelOrnith-1.5-35B-A3B-GSQ-RCO-3bit-ASCII-Condensed
context65,536
thinkingon
clientv0.4.89+102
Set those in llama.cpp k8 v4 -1 budget, then:
llm-benchmark benchmark --model "Ornith-1.5-35B-A3B-GSQ-RCO-3bit-ASCII-Condensed" --tool "llama.cpp k8 v4 -1 budget"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.