How much VRAM does Gemma 4 31B need?

In Q4_K_M with an 8k context, 19.7 GB: weights 17.1 GB, context cache 1.4 GB and about 1 GB of runtime memory. In BF16, 59.9 GB.

Does Gemma 4 31B run on an RTX 4090 with 24 GB?

Yes. In Q4_K_M the model takes 19.7 GB and fits in 24 GB.

How much does it cost to run Gemma 4 31B?

The cheapest fitting server right now is 2× RTX 3060 12 GB, from $0.174/h. Billing is per minute: stop the server and only its disk is billed.

Which quantisation should I pick?

Q4_K_M is the chat default: close to the original quality at a third of BF16's size. Q5_K_M and Q6_K are more accurate, Q8_0 is almost the original. For vLLM use FP8 or BF16.

Gemma 4 31B: how much VRAM it needs and which GPU runs it

Gemma 4 31B in Q4_K_M with an 8k context takes 19.7 GB of GPU memory. The cheapest option right now is 2× RTX 3060 12 GB, from $0.174/h.

Find a server Open in the calculator

VRAM by quantisation

The weight file and the total GPU memory with the context cache. One GPU, one request.

Quantisation	File	8K context	32K context	128K context	Fits on
BF16	57.2	59.9	61.7	69.2	RTX PRO 5000 72 GB
Q8_0	30.4	33.1	34.9	42.4	A100 PCIe 40 GB
Q6_K	23.5	26.1	28.0	35.5	Tesla V100 32 GB
Q5_K_M	20.2	22.8	24.7	32.2	RTX 3090 24 GB
Q4_K_M	17.1	19.7

File sizes checked against Hugging Face on 2026-10-19. 1 GB here is 1024³ bytes, like GPU memory. Hugging Face lists decimal gigabytes, so its numbers are 7% larger.

Gemma 4 31B: how much VRAM it needs and which GPU runs it

VRAM by quantisation

Gemma 4 31B: how much VRAM it needs and which GPU runs it

VRAM by quantisation

Context cache

Cheapest GPUs that run it

How to run it on gpu.nz

Questions