inclusionAI · First MLX build 29 Apr 2026
Ling-2.6-flash
MLX
Text mit
A 104B parameter text generation model from inclusionAI, with 6 MLX builds, from 4-bit DWQ to 8-bit.
- Parameters
- 104B From Hugging Face
- Quantisation
- 4-bit DWQ Ling-2.6-flash-mlx-4bit-DWQ
- Memory needed
- 68 GB Estimate, unified memory
- Download
- 58.6 GB Weights, estimated
- Downloads
- 104 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 68 GB at 4-bit DWQ
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-2.6-flash-mlx-4bit-DWQ --prompt "Hello"MLX builds
6 on mlx-community| Ling-2.6-flash-mlx-4bit-DWQ | 4-bit DWQ | 58.6 GB | 68 GB | 104 |
|---|---|---|---|---|
| Ling-2.6-flash-mlx-4bit | 4-bit | 58.6 GB | 68 GB | 54 |
| Ling-2.6-flash-mlx-4bit-gs32 | 4-bit | 58.6 GB | 68 GB | 49 |
| Ling-2.6-flash-mlx-5bit | 5-bit | 71.6 GB | 83 GB | 31 |
| Ling-2.6-flash-mlx-6bit | 6-bit | 84.7 GB | 97 GB | 46 |
| Ling-2.6-flash-mlx-8bit | 8-bit | 111 GB | 126 GB | 40 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.