inclusionAI · First MLX build 25 Nov 2025
LLaDA2.0-flash
MLX
Text apache-2.0
A 103B parameter text generation model from inclusionAI, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 103B From Hugging Face
- Quantisation
- 4-bit LLaDA2.0-flash-4bit
- Memory needed
- 67 GB Estimate, unified memory
- Download
- 57.9 GB Weights, estimated
- Downloads
- 28 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 67 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/LLaDA2.0-flash-4bit --prompt "Hello"MLX builds
3 on mlx-community| LLaDA2.0-flash-4bit | 4-bit | 57.9 GB | 67 GB | 28 |
|---|---|---|---|---|
| LLaDA2.0-flash-6bit | 6-bit | 83.6 GB | 96 GB | 19 |
| LLaDA2.0-flash-8bit | 8-bit | 109 GB | 125 GB | 23 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.