Can I run this LLM?
Can a NVIDIA RTX 5090 (32GB) run Gemma 3 27B?
Gemma · Gemma · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 3 27B at Q6_K · 22.2 GB · 48–71 tok/s on a NVIDIA RTX 5090 (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.5 GB | 82–123 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 69–104 tok/s | Runs great |
| Q4_K_M | 16.6 GB | 60–89 tok/s | Runs great |
| Q5_K_M | 19.3 GB | 53–80 tok/s | Runs great |
| Q6_K | 22.2 GB | 48–71 tok/s | Runs great |
| Q8_0 | 28.7 GB | 38–58 tok/s | Won't fit |
| FP16 | 54.0 GB | 22–33 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsGemma 3 27B on other machinesWhat to buy to run it →
Ran Gemma 3 27B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →