Google · 33B · Dense
Gemma 4 flagship instruct model (official)
92.5K downloads
29 likes
2026-04 256K context
Use Cases
chat vision reasoning
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q4_K_M | 4 | 17.4 GB | good | — |
| Q6_K | 6 | 25.9 GB | excellent | — |
| Q8_0 | 8 | 34.3 GB | excellent | — |
GPUs that run Gemma 4 31B IT
Gemma 4 31B IT needs about 17.4 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 24 GB of VRAM or more (35 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 24 GB | RTX 4090 , RX 7900 XTX , RTX 3090 Ti |
| 32 GB | RTX 5090 , RTX 5000 Ada , Tesla V100 32GB |
About this model
Gemma 4 flagship instruct model (official)