Benchmark result
unsloth/gemma-4-E4B-it-qat-mobile-GGUF on NVIDIA GeForce RTX 4070 — 72.6 tok/s
Measured with llama.cpp unsloth-studio/v0.1.810-beta on September 18, 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
3rd fastest of 3 runs of this model on NVIDIA GeForce RTX 4070 · median 73.6 tok/s.
sort
- 177.4tok/s29.3Unsloth Studio · UD-Q2_K_XL · KV f16
- 273.6tok/s29.5llama.cpp
- 372.6tok/s23.4llama.cppthis run
Reproduce this run
toolllama.cpp unsloth-studio/v0.1.810-beta
modelunsloth/gemma-4-E4B-it-qat-mobile-GGUF
context131,072
thinkingon
samplingtemperature 1 · top_p 0.949999988079071 · top_k 64 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.59+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/gemma-4-E4B-it-qat-mobile-GGUF" --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.