inflatebot · First MLX build 18 May 2025
MN-12B-Mag-Mell-R1
MLX
Text
A 12B parameter text generation model from inflatebot, with one MLX build at 6-bit.
- Parameters
- 12B From Hugging Face
- Quantisation
- 6-bit MN-12B-Mag-Mell-R1-6bit
- Memory needed
- 14 GB Estimate, unified memory
- Download
- 10.0 GB Weights, estimated
- Downloads
- 179 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 14 GB at 6-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/MN-12B-Mag-Mell-R1-6bit --prompt "Hello"MLX builds
1 on mlx-community| MN-12B-Mag-Mell-R1-6bit | 6-bit | 10.0 GB | 14 GB | 179 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.