gemma-4-31B-it

Gemma family · 33.0B params

Evidence: 3 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 16, 2026 · last recorded Sep 4, 2026. What these labels mean.

What the gemma-4-31B-it numbers mean

The fastest verified result on our board is 28.3 output tok/s on an CMP 170HX at NVFP4 with a 32768-token context. That is about 35.4 ms per generated token — 500 tokens takes roughly 17.7 seconds. Prompt processing on the same record runs at 967.9 tok/s, so a 2,000-token prompt is read in about 2.1 seconds. Peak VRAM was measured at 58.7 GB. Across the 4 records we hold for this model the range is 15.8–28.3 tok/s on 4 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does gemma-4-31B-it need?

gemma-4-31B-it has 33.0B 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-4-31B-it's parameter count. Full benchmark board.

All benchmarks Methodology