Can the RTX 5090 run Gemma 4 31B?

Yes. Gemma 4 31B fits the RTX 5090's 32 GB at Q4_K_M (about 20.8 GB needed), running at an estimated 54 tok/s. There's room for up to Q5_K_M if you want higher quality.

VRAM

32 GB

Needs at Q4

20.8 GB

Headroom

11.2 GB

Speed (Q4_K_M)

~54 tok/s

Every quantization

Gemma 4 31B (32.7B) on 32 GB

Quant	Weights	Needs	Fit	Est. speed
Q4_K_M	19 GB	20.8 GB	Fits	~54 tok/s
Q5_K_M	23 GB	24.8 GB	Fits	~45 tok/s
Q8_0	35 GB	36.8 GB	Too big	-
FP16	65 GB	66.8 GB	Too big	-

Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 5090's 1792 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.

Run it

Copy, paste, go

llama-server -hf google/gemma-4-31B-it-qat-q4_0-gguf -ngl 99

Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Gemma 4 31B details →

Compare

Same model, other hardware - and other models on this card

Gemma 4 31B on other hardware

RTX 5090 D~54 tok/s
RTX 6000D~47 tok/s
RTX 4090~33 tok/s
RTX 3090~29 tok/s
Radeon RX 7900 XTX~29 tok/s
MacBook Pro 16" M4 Max~16 tok/s
Arc Pro B60~14 tok/s
DGX Spark (GB10)~8.3 tok/s

Also runs on the RTX 5090

RTX 5090 specs →Everything the RTX 5090 can run →

Frequently asked

Quick answers

Can the NVIDIA RTX 5090 run Gemma 4 31B?

Yes. Gemma 4 31B fits the RTX 5090's 32 GB at Q4_K_M (about 20.8 GB needed), running at an estimated 54 tok/s. There's room for up to Q5_K_M if you want higher quality.

How much VRAM does Gemma 4 31B need?

About 19 GB of weights at Q4_K_M, 35 GB at Q8_0 and 65 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.

How fast is Gemma 4 31B on the RTX 5090?

Roughly 54 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 5090's 1792 GB/s memory bandwidth.