inclusionAI · First MLX build 27 Oct 2026
Ling-3.1-flash-1019
MLX
Text mit
A 572B parameter text generation model from inclusionAI, with 4 MLX builds, from 2-bit to 4-bit.
- Parameters
- 572B From Hugging Face
- Quantisation
- 4-bit Ling-3.1-flash-1019-oQ4e-mtp
- Memory needed
- 362 GB Estimate, unified memory
- Download
- 322 GB Weights, estimated
- Downloads
- 623 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 362 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-3.1-flash-1019-oQ4e-mtp --prompt "Hello"MLX builds
4 on mlx-community| Ling-3.1-flash-1019-oQ2e-mtp | 2-bit | 179 GB | 202 GB | 553 |
|---|---|---|---|---|
| Ling-3.1-flash-1019-oQ2.5e-mtp | 2-bit | 179 GB | 202 GB | 497 |
| Ling-3.1-flash-1019-oQ3e-mtp | 3-bit | 250 GB | 282 GB | 486 |
| Ling-3.1-flash-1019-oQ4e-mtp | 4-bit | 322 GB | 362 GB | 623 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.