Benchmark result
unsloth/gemma-4-26B-A4B-it-qat-GGUF on 2× NVIDIA GeForce RTX 3080 — 31.4 tok/s
Measured with Unsloth Studio on September 29, 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.
How this run compares
2nd fastest of 2 runs of this model on 2× NVIDIA GeForce RTX 3080 · Multi-GPU · median 36.1 tok/s.
sort
- 140.8tok/s70.9Unsloth Studio · UD-Q4_K_XL · KV f16
- 231.4tok/s62.0Unsloth Studio · UD-Q4_K_XL · KV f16this run
Reproduce this run
toolUnsloth Studio
modelunsloth/gemma-4-26B-A4B-it-qat-GGUF (UD-Q4_K_XL)
context147,072
kv cachef16 (assumed default)
thinkingon
samplingtemperature 1 · top_p 0.95 · top_k 64 · min_p 0 · presence_penalty 0
clientv0.4.85+101
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/gemma-4-26B-A4B-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.