MLX Community · First MLX build 16 Aug 2025
Kimi-VL-A3B-Thinking-2506
MLX
TextVision mit
A 16B parameter vision and text model, with 4 MLX builds, from bf16 to 5-bit.
- Parameters
- 16B From Hugging Face
- Quantisation
- 6-bit Kimi-VL-A3B-Thinking-2506-6bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 200 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 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/Kimi-VL-A3B-Thinking-2506-6bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| Kimi-VL-A3B-Thinking-2506-bf16 | bf16 | 32.8 GB | 39 GB | 146 |
|---|---|---|---|---|
| Kimi-VL-A3B-Thinking-2506-6bit | 6-bit | — | — | 200 |
| Kimi-VL-A3B-Thinking-2506-8bit | 8-bit | — | — | 199 |
| Kimi-VL-A3B-Thinking-2506-5bit | 5-bit | — | — | 149 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.