4-bit Open on Hugging Face
Parameters
947B
Weights (est.)
≈ 549 GB
Mac memory (est.)
> 512 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/Inkling-mlx-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- thinkingmachines/Inkling (finetune)
- Vendor
- thinkingmachines
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 270 in the last 30 days · 4.2K all time · 7 likes
- Published
- 2026-07-16 · updated 2026-07-24 (3mo ago)
- Tags
- inkling_mm_model, inkling, multimodal, text-generation
Other MLX builds of thinkingmachines/Inkling
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Inkling-mlx-2bit | 2-bit | ≈ 315 GB | 512 GB+ | 237 |
| Inkling-mlx-4bit (this one) | 4-bit | ≈ 549 GB | > 512 GB | 270 |