Can I run this LLM?
Can a NVIDIA RTX 5080 (16GB) run Gemma 3 27B?
Gemma · Gemma · estimated for a 16.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Gemma 3 27B at Q2_K · 10.5 GB · 49–73 tok/s on a NVIDIA RTX 5080 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.5 GB | 49–73 tok/s | Tight / slow |
| Q3_K_M | 13.4 GB | 41–61 tok/s | Won't fit |
| Q4_K_M | 16.6 GB | 34–52 tok/s | Won't fit |
| Q5_K_M | 19.3 GB | 30–46 tok/s | Won't fit |
| Q6_K | 22.2 GB | 27–41 tok/s | Won't fit |
| Q8_0 | 28.7 GB | 22–32 tok/s | Won't fit |
| FP16 | 54.0 GB | 12–18 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5080 (16GB) runsGemma 3 27B on other machinesWhat to buy to run it →
Ran Gemma 3 27B on a NVIDIA RTX 5080 (16GB)? Add your real numbers →