Benchmark result
gemma-4-26b-a4b-q4kxl on AMD Radeon RX 7900 XTX — 171.1 tok/s
Measured with llama.cpp b342-c7bda03 on September 5, 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 3 runs of this model on AMD Radeon RX 7900 XTX · median 170.9 tok/s.
sort
- 1171.1tok/s69.5llama.cppthis run
- 2170.9tok/s74.2llama.cpp
- 3167.7tok/s65.0llama.cpp
Reproduce this run
toolllama.cpp b342-c7bda03
modelgemma-4-26b-a4b-q4kxl
context65,536
thinkingon
clientv0.4.46+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "gemma-4-26b-a4b-q4kxl" --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.