Benchmark result
unsloth/gemma-4-12B-it-qat-GGUF on NVIDIA GeForce RTX 4070 — 82.0 tok/s
Measured with Unsloth Studio on September 27, 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 6 runs of this model on NVIDIA GeForce RTX 4070 · median 52.3 tok/s.
sort
- 182.0tok/s72.3Unsloth Studio · UD-Q4_K_XL · KV q8_0this run
- 274.0tok/s71.7Unsloth Studio · UD-Q4_K_XL · KV q4_0
- 353.3tok/s69.7Unsloth Studio · UD-Q4_K_XL · KV f16
- 451.4tok/s67.8llama.cpp
- 550.4tok/s73.8Unsloth Studio · UD-Q4_K_XL · KV f16
- 650.1tok/s69.7llama.cpp
unsloth/gemma-4-12B-it-qat-GGUF on other hardware
Reproduce this run
toolUnsloth Studio
modelunsloth/gemma-4-12B-it-qat-GGUF (UD-Q4_K_XL)
context100,000
kv cacheq8_0
thinkingon
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 64 · min_p 0 · presence_penalty 0
clientv0.4.82+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/gemma-4-12B-it-qat-GGUF" --tool "Unsloth Studio"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.