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 · 112–168 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 5.7 GB | 234–350 tok/s | Runs great |
| Q4_K_M | 7.1 GB | 215–323 tok/s | Runs great |
| Q5_K_M | 8.4 GB | 201–301 tok/s | Runs great |
| Q6_K | 9.8 GB | 188–281 tok/s | Runs great |
| Q8_0 | 12.7 GB | 165–247 tok/s | Runs great |
| FP16 | 23.8 GB | 112–168 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 →