Benchmark result
gemma-4-26b-a4b on 2× AMD Radeon AI PRO R9700 — 197.9 tok/s
Measured with llama.cpp manual on November 13, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
2nd fastest of 2 runs of this model on 2× AMD Radeon AI PRO R9700 · Multi-GPU · median 198.8 tok/s.
sort
- 1199.7tok/s73.6llama.cpp
- 2197.9tok/s75.1llama.cppthis run
Reproduce this run
toolllama.cpp manual
modelgemma-4-26b-a4b
context65,536
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "gemma-4-26b-a4b" --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.