ServiceNow-AI · First MLX build 2 Oct 2025
Apriel-1.5-15b-Thinker
MLX
TextVision mit
A 15B parameter vision and text model from ServiceNow-AI, with 3 MLX builds, from 2-bit to 6-bit.
- Parameters
- 15B From Hugging Face
- Quantisation
- 3-bit Apriel-1.5-15b-Thinker-3bit-MLX
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 42 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/Apriel-1.5-15b-Thinker-3bit-MLX --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| Apriel-1.5-15b-Thinker-2bit-MLX | 2-bit | 5.3 GB | 8 GB | 40 |
|---|---|---|---|---|
| Apriel-1.5-15b-Thinker-3bit-MLX | 3-bit | — | — | 42 |
| Apriel-1.5-15b-Thinker-6bit-MLX | 6-bit | — | — | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.