Rent a GPU

Can the NVIDIA RTX 5090 run Gemma 2 27B?

RTX 5090 × Gemma 2 27B8K context
YesRuns fully on the GPU
Memory at Q6_K26 GB of 32 GB
Weights 22.3 GBKV cache 3.1 GBRuntime 0.6 GB
QuantQ6_KExcellent
Memory26 GBof 32 GB usable
Speed~48tokens per second
  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 2 27B fully in VRAM at Q6_K (excellent), using about 26 GB of the 32 GB available, at roughly 48 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 2 27B:

ollama run gemma2:27b

Ollama's default download is Q4_K_M (about 20.2 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5090? Run Gemma 2 27B 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 quality58.1 GBToo big—
Q8_0Near-lossless32.6 GBToo big—
Q6_KExcellent26 GBFits~48 tok/s
Q5_K_MVery good23 GBFits~56 tok/s
Q4_K_MGood, most popular20.2 GBFits~65 tok/s
Q3_K_MNoticeably degraded17 GBFits~81 tok/s
Q2_KHeavily degraded13.9 GBFits~105 tok/s

GPUs that run Gemma 2 27B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Gemma 2 27B?

Yes. The NVIDIA RTX 5090 can run Gemma 2 27B fully in VRAM at Q6_K (excellent), using about 26 GB of the 32 GB available, at roughly 48 tokens/second.

How much VRAM does Gemma 2 27B need?

About 20.2 GB at Q4_K_M with 8,192 tokens of context, and about 58.1 GB at full FP16 precision.

How fast is Gemma 2 27B on the NVIDIA RTX 5090?

Roughly 48 tokens per second at Q6_K, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.