8-bit Open on Hugging Face
Parameters
315M
Weights (est.)
≈ 416 MB
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.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/CodeFormulaV2-mlx-q8 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- docling-project/CodeFormulaV2 (quantized)
- Vendor
- docling-project
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- cdla-permissive-2.0
- Downloads
- 25 in the last 30 days · 134 all time · 0 likes
- Published
- 2026-05-16 · updated 2026-05-16 (5mo ago)
- Languages
- en
- Tags
- idefics3, mlx-vlm, quantized
Other MLX builds of docling-project/CodeFormulaV2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| CodeFormulaV2-mlx-q8 (this one) | 8-bit | ≈ 416 MB | 8 GB+ | 25 |
| CodeFormulaV2-mlx-bf16 | bf16 | ≈ 631 MB | 8 GB+ | 84 |