Benchmark result
ggml-org/gemma-4-E4B-it-GGUF:Q4_0 on NVIDIA GeForce RTX 2070 SUPER — 86.9 tok/s
Measured with llama.cpp b11706-f74e2fa6a on October 23, 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.
Reproduce this run
toolllama.cpp b11706-f74e2fa6a
modelggml-org/gemma-4-E4B-it-GGUF:Q4_0 (Q4_0)
context32,768
think limitnone
samplingtemperature 1 · top_p 0.949999988079071 · top_k 64 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.97+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ggml-org/gemma-4-E4B-it-GGUF:Q4_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.