Can I run this LLM?
Can a NVIDIA A100 (80GB) run Gemma 4 12B?
Gemma · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 12B at FP16 · 23.8 GB · 53–80 tok/s on a NVIDIA A100 (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 5.7 GB | 148–222 tok/s | Runs great |
| Q4_K_M | 7.1 GB | 130–194 tok/s | Runs great |
| Q5_K_M | 8.4 GB | 117–175 tok/s | Runs great |
| Q6_K | 9.8 GB | 105–158 tok/s | Runs great |
| Q8_0 | 12.7 GB | 88–131 tok/s | Runs great |
| FP16 | 23.8 GB | 53–80 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA A100 (80GB) runsGemma 4 12B on other machinesWhat to buy to run it →
Ran Gemma 4 12B on a NVIDIA A100 (80GB)? Add your real numbers →