bf16 Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 16.0 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- google/gemma-4-e4b
- Vendor
- Google · Gemma
- Task
- Any to any
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 45 in the last 30 days · 2.4K all time · 1 likes
- Published
- 2026-04-02 · updated 2026-04-03 (7mo ago)
- Tags
- gemma4
Other MLX builds of google/gemma-4-e4b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-e4b-4bit | 4-bit | ≈ 5.2 GB | 8 GB+ | 454 |
| gemma-4-e4b-5bit | 5-bit | ≈ 6.2 GB | 16 GB+ | 59 |
| gemma-4-e4b-6bit | 6-bit | ≈ 7.1 GB | 16 GB+ | 58 |
| gemma-4-e4b-8bit | 8-bit | ≈ 9.0 GB | 16 GB+ | 212 |
| gemma-4-e4b-mxfp8 | MXFP8 | ≈ 9.0 GB | 16 GB+ | 44 |
| gemma-4-e4b-bf16 (this one) | bf16 | ≈ 16.0 GB | 24 GB+ | 45 |