Can the NVIDIA RTX 5090 run Gemma 2 27B?
Yes
QuantQ6_KExcellent
Memory26 GBof 32 GB
Speed~48tokens/s
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 in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 58.1 GB | Too big | — |
| Q8_0 | Near-lossless | 32.6 GB | Too big | — |
| Q6_K | Excellent | 26 GB | Fits | ~48 tok/s |
| Q5_K_M | Very good | 23 GB | Fits | ~56 tok/s |
| Q4_K_M | Good, most popular | 20.2 GB | Fits | ~65 tok/s |
| Q3_K_M | Noticeably degraded | 17 GB | Fits | ~81 tok/s |
| Q2_K | Heavily degraded | 13.9 GB | Fits | ~105 tok/s |
How to run Gemma 2 27B on the NVIDIA RTX 5090
With Ollama installed, one command downloads and starts it:
ollama run gemma2:27bOllama'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.
GPUs that run Gemma 2 27B comfortably
- NVIDIA RTX 3090 (24 GB)
- AMD Radeon RX 7900 XTX (24 GB)
- NVIDIA RTX 4090 (24 GB)
- Apple M2 Pro (32GB)
- Apple M4 Pro (48GB)
Models that run well on the NVIDIA RTX 5090
Run it in the cloud
Don't want to buy hardware? Run Gemma 2 27B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.