MXFP4 Open on Hugging Face
Parameters
5.1B
Weights (est.)
≈ 3.6 GB
Mac memory (est.)
8 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-e2b
- Vendor
- Google · Gemma
- Task
- Any to any
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 31 in the last 30 days · 977 all time · 0 likes
- Published
- 2026-04-02 · updated 2026-04-03 (7mo ago)
- Tags
- gemma4
Other MLX builds of google/gemma-4-e2b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-e2b-4bit | 4-bit | ≈ 3.6 GB | 8 GB+ | 435 |
| gemma-4-e2b-nvfp4 | 4-bit | ≈ 3.6 GB | 8 GB+ | 32 |
| gemma-4-e2b-mxfp4 (this one) | MXFP4 | ≈ 3.6 GB | 8 GB+ | 31 |
| gemma-4-e2b-5bit | 5-bit | ≈ 4.2 GB | 8 GB+ | 41 |
| gemma-4-e2b-6bit | 6-bit | ≈ 4.7 GB | 8 GB+ | 37 |
| gemma-4-e2b-8bit | 8-bit | ≈ 5.9 GB | 16 GB+ | 130 |
| gemma-4-e2b-mxfp8 | MXFP8 | ≈ 5.9 GB | 16 GB+ | 37 |
| gemma-4-e2b-bf16 | bf16 | ≈ 10.2 GB | 16 GB+ | 37 |