inclusionAI · First MLX build 11 Sept 2025
Ling-mini-2.0
MLX
Text mit
A 16B parameter text generation model from inclusionAI, with 6 MLX builds, from 2-bit DWQ to 8-bit.
- Parameters
- 16B From Hugging Face
- Quantisation
- 4-bit Ling-mini-2.0-4bit
- Memory needed
- 13 GB Estimate, unified memory
- Download
- 9.1 GB Weights, estimated
- Downloads
- 171 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 13 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-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Ling-mini-2.0-4bit --prompt "Hello"MLX builds
6 on mlx-community| Ling-mini-2.0-2bit-DWQ | 2-bit DWQ | 5.1 GB | 8 GB | 56 |
|---|---|---|---|---|
| Ling-mini-2.0-2bit | 2-bit | 5.1 GB | 8 GB | 41 |
| Ling-mini-2.0-3bit | 3-bit | 7.1 GB | 10 GB | 35 |
| Ling-mini-2.0-4bit | 4-bit | 9.1 GB | 13 GB | 171 |
| Ling-mini-2.0-6bit | 6-bit | 13.2 GB | 17 GB | 28 |
| Ling-mini-2.0-8bit | 8-bit | 17.3 GB | 22 GB | 41 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.