Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Gemma 4 12B?
Gemma · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 12B at FP16 · 23.8 GB · 105–158 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 5.1 GB | 211–316 tok/s | Runs great |
| Q4_K_M | 7.2 GB | 190–284 tok/s | Runs great |
| Q5_K_M | 8.5 GB | 179–268 tok/s | Runs great |
| Q6_K | 9.8 GB | 168–253 tok/s | Runs great |
| Q8_0 | 12.7 GB | 150–225 tok/s | Runs great |
| FP16 | 23.8 GB | 105–158 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsGemma 4 12B on other machinesWhat to buy to run it →
Ran Gemma 4 12B on a AMD Instinct MI300X (192GB)? Add your real numbers →