Benchmark result
ConwayResearch/Underdog-Saluki-27B-1.0 on AMD Radeon RX 9070/9070 XT/9070 GRE — 43.5 tok/s
Measured with llama.cpp b11388-050439614 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 b11388-050439614
modelConwayResearch/Underdog-Saluki-27B-1.0
context32,768
thinkingon
effortxhigh
think limit6,144 tokens
samplingtemperature 0.699999988079071 · top_p 0.949999988079071 · top_k 20 · min_p 0.10000000149011612 · presence_penalty 0 · repeat_penalty 1
clientv0.4.89+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ConwayResearch/Underdog-Saluki-27B-1.0" --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.