Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Gemma 4 31B?
Gemma · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 31B at FP16 · 61.4 GB · 49–74 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.2 GB | 126–190 tok/s | Runs great |
| Q4_K_M | 18.6 GB | 108–162 tok/s | Runs great |
| Q5_K_M | 21.9 GB | 99–148 tok/s | Runs great |
| Q6_K | 25.3 GB | 91–136 tok/s | Runs great |
| Q8_0 | 32.6 GB | 78–117 tok/s | Runs great |
| FP16 | 61.4 GB | 49–74 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a AMD Instinct MI300X (192GB)? Add your real numbers →