PRIME-RL · First MLX build 18 May 2026
P1-VL-30B-A3B
MLX
TextVision apache-2.0
A 31B parameter vision and text model from PRIME-RL, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 31B From Hugging Face
- Quantisation
- bf16 P1-VL-30B-A3B-bf16
- Memory needed
- 72 GB Estimate, unified memory
- Download
- 62.1 GB Weights, estimated
- Downloads
- 38 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 72 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/P1-VL-30B-A3B-bf16 --image photo.jpg --prompt "Describe this image"MLX builds
8 on mlx-community| P1-VL-30B-A3B-4bit | 4-bit | 18.3 GB | 23 GB | 22 |
|---|---|---|---|---|
| P1-VL-30B-A3B-mxfp4 | MXFP4 | 18.3 GB | 23 GB | 17 |
| P1-VL-30B-A3B-nvfp4 | 4-bit | 18.3 GB | 23 GB | 15 |
| P1-VL-30B-A3B-5bit | 5-bit | 22.1 GB | 27 GB | 14 |
| P1-VL-30B-A3B-6bit | 6-bit | 25.9 GB | 31 GB | 17 |
| P1-VL-30B-A3B-8bit | 8-bit | 33.5 GB | 40 GB | 33 |
| P1-VL-30B-A3B-mxfp8 | MXFP8 | 33.5 GB | 40 GB | 16 |
| P1-VL-30B-A3B-bf16 | bf16 | 62.1 GB | 72 GB | 38 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.