Gemma 4
gemma-4-E4B-it
Google DeepMind · open-permissive apache-2.0
| Parameters (B) | 7.996 |
|---|---|
| Architecture | dense |
| Layers / KV heads / head dim | 42 / 2 / 256 |
| Context window | 131072 |
| Modalities | in: text, image, audio; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 6.1 GiB. On a machine with 64 GiB system RAM and no discrete GPU: CPU-only, slow. Limiting factor: No GPU VRAM; fits in system RAM but inference will be CPU-bound.
Scores
No Tier A comparable scores ingested yet for this model.
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/google/gemma-4-E4B-it (retrieved 2026-08-10)
HF: google/gemma-4-E4B-it · snapshot 2026-08-10