Rent a GPU

Can the NVIDIA RTX 5090 run Gemma 4 31B?

RTX 5090 × Gemma 4 31B8K context
YesRuns fully on the GPU
Memory at Q6_K27.4 GB of 32 GB
Weights 25.7 GBKV cache 1.2 GBRuntime 0.6 GB
QuantQ6_KExcellent
Speed~42tokens per second
Max context116Ktokens that fit at Q6_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 5090 can run Gemma 4 31B fully in VRAM at Q6_K (excellent), using about 27.4 GB of the 32 GB available, at roughly 42 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 4 31B:

ollama run gemma4:31b

Ollama's default download is Q4_K_M (about 20.8 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 5090

Run it in the cloud

No NVIDIA RTX 5090? Run Gemma 4 31B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 32 GB the NVIDIA RTX 5090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality64.4 GBToo big—
Q8_0Near-lossless35 GBToo big—
Q6_KExcellent27.4 GBFits~42 tok/s
Q5_K_MVery good24 GBFits~48 tok/s
Q4_K_MGood, most popular20.8 GBFits~57 tok/s
Q3_K_MNoticeably degraded17.1 GBFits~70 tok/s
Q2_KHeavily degraded13.5 GBFits~92 tok/s

Measured speed from real RTX 5090 owners

Tokens per second that people measured on their own NVIDIA RTX 5090, next to our estimate.

No one has measured Gemma 4 31B on the NVIDIA RTX 5090 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5090? Add your real speed

One command times Gemma 4 31B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- gemma4:31b

Windows (PowerShell)

$env:GPUFIT_MODEL="gemma4:31b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Gemma 4 31B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Gemma 4 31B?

Yes. The NVIDIA RTX 5090 can run Gemma 4 31B fully in VRAM at Q6_K (excellent), using about 27.4 GB of the 32 GB available, at roughly 42 tokens/second.

How much VRAM does Gemma 4 31B need?

About 20.8 GB at Q4_K_M with 8,192 tokens of context, and about 64.4 GB at full FP16 precision.

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

Roughly 42 tokens per second at Q6_K, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.