Rent a GPU

Can the NVIDIA RTX 5080 run Gemma 2 9B?

RTX 5080 × Gemma 2 9B8K context
YesRuns fully on the GPU
Memory at Q8_013.2 GB of 16 GB
Weights 9.8 GBKV cache 2.8 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory13.2 GBof 16 GB usable
Speed~59tokens 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 5080 can run Gemma 2 9B fully in VRAM at Q8_0 (near-lossless), using about 13.2 GB of the 16 GB available, at roughly 59 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 Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5080? 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 16 GB the NVIDIA RTX 5080 can use.

QuantQualityMemoryFits?Speed
FP16Full quality21.9 GBToo big—
Q8_0Near-lossless13.2 GBFits~59 tok/s
Q6_KExcellent11 GBFits~76 tok/s
Q5_K_MVery good10 GBFits~88 tok/s
Q4_K_MGood, most popular9 GBFits~103 tok/s
Q3_K_MNoticeably degraded7.9 GBFits~128 tok/s
Q2_KHeavily degraded6.9 GBFits~166 tok/s

GPUs that run Gemma 2 9B comfortably

Models that run well on the NVIDIA RTX 5080

Frequently asked questions

Can NVIDIA RTX 5080 run Gemma 2 9B?

Yes. The NVIDIA RTX 5080 can run Gemma 2 9B fully in VRAM at Q8_0 (near-lossless), using about 13.2 GB of the 16 GB available, at roughly 59 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 5080?

Roughly 59 tokens per second at Q8_0, estimated from the NVIDIA RTX 5080's 960 GB/s memory bandwidth.