Rent a GPU

Can the NVIDIA RTX 5090 run Gemma 2 9B?

RTX 5090 × Gemma 2 9B8K context
YesRuns fully on the GPU
Memory at FP1621.9 GB of 32 GB
Weights 18.5 GBKV cache 2.8 GBRuntime 0.6 GB
QuantFP16Full quality
Memory21.9 GBof 32 GB usable
Speed~58tokens 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 9B fully in VRAM at FP16 (full quality), using about 21.9 GB of the 32 GB available, at roughly 58 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 2 9B:

ollama run gemma2:9b

Ollama's default download is Q4_K_M (about 9 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5090? Run Gemma 2 9B 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 quality21.9 GBFits~58 tok/s
Q8_0Near-lossless13.2 GBFits~110 tok/s
Q6_KExcellent11 GBFits~142 tok/s
Q5_K_MVery good10 GBFits~164 tok/s
Q4_K_MGood, most popular9 GBFits~192 tok/s
Q3_K_MNoticeably degraded7.9 GBFits~238 tok/s
Q2_KHeavily degraded6.9 GBFits~310 tok/s

GPUs that run Gemma 2 9B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Gemma 2 9B?

Yes. The NVIDIA RTX 5090 can run Gemma 2 9B fully in VRAM at FP16 (full quality), using about 21.9 GB of the 32 GB available, at roughly 58 tokens/second.

How much VRAM does Gemma 2 9B need?

About 9 GB at Q4_K_M with 8,192 tokens of context, and about 21.9 GB at full FP16 precision.

How fast is Gemma 2 9B on the NVIDIA RTX 5090?

Roughly 58 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.