Benchmark result
unsloth/gemma-4-12b-it-GGUF on NVIDIA GeForce RTX 5050 Laptop GPU — 26.3 tok/s
Measured with Unsloth Studio on November 3, 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.
Reproduce this run
toolUnsloth Studio
modelunsloth/gemma-4-12b-it-GGUF (Q3_K_S)
context32,768
kv cacheq4_1
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 64 · min_p 0 · presence_penalty 0
clientv0.4.98+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/gemma-4-12b-it-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.