Benchmark result
Ornith-1.5-9B-Q8_0 on AMD Radeon RX 9070/9070 XT/9070 GRE — 54.9 tok/s
Measured with vLLM on August 28, 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
Ornith-1.5-9B-Q8_0 on other hardware
Reproduce this run
toolvLLM
modelOrnith-1.5-9B-Q8_0 (Q8_0)
context8,192
clientv0.4.44+97
Set those in vLLM, then:
llm-benchmark benchmark --model "Ornith-1.5-9B-Q8_0" --tool "vLLM"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.