Can I run this LLM?
Can a Desktop CPU, DDR5 dual-channel (32GB) run Gemma 4 31B?
Gemma · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Gemma 4 31B at Q3_K_M · 13.2 GB · 2–2 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.2 GB | 2–2 tok/s | Tight / slow |
| Q4_K_M | 18.6 GB | 1–2 tok/s | Won't fit |
| Q5_K_M | 21.9 GB | 1–2 tok/s | Won't fit |
| Q6_K | 25.3 GB | 1–1 tok/s | Won't fit |
| Q8_0 | 32.6 GB | 1–1 tok/s | Won't fit |
| FP16 | 61.4 GB | 0–1 tok/s | Won't fit |
Open the full calculator →Everything a Desktop CPU, DDR5 dual-channel (32GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →