4-bit Open on Hugging Face
Parameters
4.1B
Weights (est.)
≈ 2.3 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
- microsoft/Lens (finetune)
- Vendor
- Microsoft · Phi
- Task
- Text to image
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 13 in the last 30 days · 285 all time · 1 likes
- Published
- 2026-05-31 · updated 2026-06-21 (4mo ago)
- Tags
- diffusion, lens, apple-silicon, quantized
Other MLX builds of microsoft/Lens
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Lens-3.8B-4bit (this one) | 4-bit | ≈ 2.3 GB | 8 GB+ | 13 |
| Lens-3.8B-8bit | 8-bit | ≈ 4.4 GB | 8 GB+ | 16 |
| Lens-3.8B-bf16 | bf16 | ≈ 8.2 GB | 16 GB+ | 25 |