Rent a GPU

Can the NVIDIA RTX 5090 run Gemma 4 26B-A4B?

RTX 5090 × Gemma 4 26B-A4B8K context
YesRuns fully on the GPU
Memory at Q8_028.3 GB of 32 GB
Weights 27.4 GBKV cache 0.3 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~266tokens per second
Max context256Kthe model's full window
  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 26B-A4B fully in VRAM at Q8_0 (near-lossless), using about 28.3 GB of the 32 GB available, at roughly 266 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 4 26B-A4B:

ollama run gemma4:26b

Ollama's default download is Q4_K_M (about 16.5 GB here). You have room for Q8_0, which is near-lossless: 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 26B-A4B 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 quality52.5 GBToo big—
Q8_0Near-lossless28.3 GBFits~266 tok/s
Q6_KExcellent22 GBFits~345 tok/s
Q5_K_MVery good19.2 GBFits~398 tok/s
Q4_K_MGood, most popular16.5 GBFits~467 tok/s
Q3_K_MNoticeably degraded13.5 GBFits~579 tok/s
Q2_KHeavily degraded10.6 GBFits~755 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 26B-A4B 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 26B-A4B 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 -- gemma4:26b

Windows (PowerShell)

$env:GPUFIT_MODEL="gemma4:26b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Gemma 4 26B-A4B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Gemma 4 26B-A4B?

Yes. The NVIDIA RTX 5090 can run Gemma 4 26B-A4B fully in VRAM at Q8_0 (near-lossless), using about 28.3 GB of the 32 GB available, at roughly 266 tokens/second.

How much VRAM does Gemma 4 26B-A4B need?

About 16.5 GB at Q4_K_M with 8,192 tokens of context, and about 52.5 GB at full FP16 precision.

How fast is Gemma 4 26B-A4B on the NVIDIA RTX 5090?

Roughly 266 tokens per second at Q8_0, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.