docling-project · First MLX build 16 May 2026
CodeFormulaV2
MLX
TextVision cdla-permissive-2.0
A 315M parameter vision and text model from docling-project, with 2 MLX builds, from 8-bit to bf16.
- Parameters
- 315M From Hugging Face
- Quantisation
- bf16 CodeFormulaV2-mlx-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 631 MB Weights, estimated
- Downloads
- 83 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/CodeFormulaV2-mlx-bf16 --image photo.jpg --prompt "Describe this image"MLX builds
2 on mlx-community| CodeFormulaV2-mlx-q8 | 8-bit | 416 MB | 3 GB | 22 |
|---|---|---|---|---|
| CodeFormulaV2-mlx-bf16 | bf16 | 631 MB | 3 GB | 83 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.