Google · 8B · 密集(Dense)
Gemma 4 balanced instruct model (official) 看看你的 GPU 或 Mac 跑不跑得動 Gemma 4 E4B IT——最低 4.5 GB,建議 7.5 GB。
2026-04256K context
| 量化 | 位元 | VRAM | 品質 | 狀態 |
|---|---|---|---|---|
| Q4_K_M | 4 | 4.6 GB | good | — |
| Q6_K | 6 | 6.6 GB | excellent | — |
| Q8_0 | 8 | 8.7 GB | excellent | — |
Can I run Gemma 4 E4B IT locally?
- Can I run Gemma 4 E4B IT locally?
- Gemma 4 E4B IT needs about 4.5 GB of memory at a minimum and 7.5 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Gemma 4 E4B IT need?
- At Q4_K_M, Gemma 4 E4B IT uses about 4.6 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.