4-bit Open on Hugging Face
Parameters
264B
Weights (est.)
≈ 153 GB
Mac memory (est.)
192 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-Small-mlx-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- thinkingmachines/Inkling-Small (finetune)
- Vendor
- thinkingmachines
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 233 in the last 30 days · 1.1K all time · 1 likes
- Published
- 2026-07-31 · updated 2026-07-31 (3mo ago)
- Tags
- inkling_mm_model, inkling, multimodal, text-generation, apple-silicon
Other MLX builds of thinkingmachines/Inkling-Small
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Inkling-Small-mlx-2bit | 2-bit | ≈ 88.4 GB | 128 GB+ | 268 |
| Inkling-Small-mlx-3bit | 3-bit | ≈ 121 GB | 192 GB+ | 109 |
| Inkling-Small-mxfp4 | MXFP4 | ≈ 149 GB | 192 GB+ | 176 |
| Inkling-Small-mlx-4bit (this one) | 4-bit | ≈ 153 GB | 192 GB+ | 233 |