thinkingmachines · First MLX build 16 Jul 2026
Inkling
MLX
TextVision apache-2.0
A 947B parameter vision and text model from thinkingmachines, with 2 MLX builds, from 2-bit to 4-bit.
- Parameters
- 947B From Hugging Face
- Quantisation
- 4-bit Inkling-mlx-4bit
- Memory needed
- 616 GB Estimate, unified memory
- Download
- 549 GB Weights, estimated
- Downloads
- 303 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 616 GB at 4-bit
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/Inkling-mlx-4bit --image photo.jpg --prompt "Describe this image"MLX builds
2 on mlx-community| Inkling-mlx-2bit | 2-bit | 315 GB | 354 GB | 264 |
|---|---|---|---|---|
| Inkling-mlx-4bit | 4-bit | 549 GB | 616 GB | 303 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.