Can the NVIDIA RTX 3080 10GB run Gemma 2 9B?
Yes
QuantQ5_K_MVery good
Memory10 GBof 10 GB
Speed~69tokens/s
Yes. The NVIDIA RTX 3080 10GB can run Gemma 2 9B fully in VRAM at Q5_K_M (very good), using about 10 GB of the 10 GB available, at roughly 69 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 21.9 GB | Too big | — |
| Q8_0 | Near-lossless | 13.2 GB | Too big | — |
| Q6_K | Excellent | 11 GB | Too big | — |
| Q5_K_M | Very good | 10 GB | Fits | ~69 tok/s |
| Q4_K_M | Good, most popular | 9 GB | Fits | ~81 tok/s |
| Q3_K_M | Noticeably degraded | 7.9 GB | Fits | ~101 tok/s |
| Q2_K | Heavily degraded | 6.9 GB | Fits | ~132 tok/s |
How to run Gemma 2 9B on the NVIDIA RTX 3080 10GB
With Ollama installed, one command downloads and starts it:
ollama run gemma2:9bOllama's default download is Q4_K_M (about 9 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.
GPUs that run Gemma 2 9B comfortably
Models that run well on the NVIDIA RTX 3080 10GB
Run it in the cloud
Don't want to buy hardware? Run Gemma 2 9B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.