gemma-4-12B-it-qat

Gemma family · 12.0B params

Evidence: 1 sourced run · 2 awaiting review · 1 independent source · first recorded Jul 21, 2026 · last recorded Aug 18, 2026. What these labels mean.

What the gemma-4-12B-it-qat numbers mean

The fastest verified result on our board is 71.2 output tok/s on an RTX 3080 at Q4_0 with a 262144-token context. That is about 14.0 ms per generated token — 500 tokens takes roughly 7.0 seconds. Prompt processing on the same record runs at 2671.1 tok/s, so a 2,000-token prompt is read in about 0.7 seconds. Peak VRAM was measured at 9.7 GB. Across the 3 records we hold for this model the range is 71.2–130.8 tok/s on 3 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does gemma-4-12B-it-qat need?

gemma-4-12B-it-qat has 12.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from gemma-4-12B-it-qat's parameter count. Full benchmark board.

All benchmarks Methodology