Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Gemma 3 12B?
Gemma · Gemma · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 3 12B at FP16 · 23.5 GB · 109–164 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.8 GB | 230–344 tok/s | Runs great |
| Q3_K_M | 6.0 GB | 214–321 tok/s | Runs great |
| Q4_K_M | 7.3 GB | 200–300 tok/s | Runs great |
| Q5_K_M | 8.5 GB | 189–283 tok/s | Runs great |
| Q6_K | 9.7 GB | 178–268 tok/s | Runs great |
| Q8_0 | 12.5 GB | 158–237 tok/s | Runs great |
| FP16 | 23.5 GB | 109–164 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsGemma 3 12B on other machinesWhat to buy to run it →
Ran Gemma 3 12B on a AMD Instinct MI300X (192GB)? Add your real numbers →