Google · 5B · Dense
Gemma 4 efficient base model (official)
79.9K downloads
424 likes
2026-04 256K context
Use Cases
vision
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 2.1 GB | low | — |
| Q3_K_M | 3 | 2.7 GB | moderate | — |
| Q4_K_M | 4 | 3.1 GB | good | — |
| Q5_K_M | 5 | 3.7 GB | good | — |
| Q6_K | 6 | 4.3 GB | excellent | — |
| Q8_0 | 8 | 5.6 GB | excellent | — |
| F16 | 16 | 10.7 GB | lossless | — |
GPUs that run Gemma 4 E2B
Gemma 4 E2B needs about 3.1 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 4 GB of VRAM or more (192 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 4 GB | RX 6500 XT , GTX 1650 SUPER , GTX 1650 Ti |
| 6 GB | RTX 2060 , Arc A380 , RX 5600 XT |
| 8 GB | RTX 5060 Ti , RX 7600 , Arc A750 |
| 10 GB | RTX 3080 |
About this model
Gemma 4 efficient base model (official)