Benchmark result
pfeifferj/Ornith-1.5-35B-A3B-GSQ-RCO-GGUF:3bit on AMD Radeon RX 9070/9070 XT/9070 GRE — 101.4 tok/s
Measured with llama.cpp b11388-050439614 on October 4, 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 9070/9070 XT/9070 GRE · median 94.8 tok/s.
sort
- 1101.4tok/s62.2llama.cppthis run
- 288.2tok/s84.4llama.cpp
Reproduce this run
toolllama.cpp b11388-050439614
modelpfeifferj/Ornith-1.5-35B-A3B-GSQ-RCO-GGUF:3bit
context32,768
think limitnone
samplingtemperature 0.6000000238418579 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "pfeifferj/Ornith-1.5-35B-A3B-GSQ-RCO-GGUF:3bit" --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.