Goekdeniz-Guelmez · First MLX build 26 Jan 2026
Josiefied-LFM2.5-1.2B-Instruct-abliterated
MLX
Text
A 1.2B parameter text generation model from Goekdeniz-Guelmez, with 5 MLX builds, from 4-bit to MXFP4.
- Parameters
- 1.2B From Hugging Face
- Quantisation
- 4-bit Josiefied-LFM2.5-1.2B-Instruct-abliterated-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 659 MB Weights, estimated
- Downloads
- 219 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/Josiefied-LFM2.5-1.2B-Instruct-abliterated-4bit --prompt "Hello"MLX builds
5 on mlx-community| Josiefied-LFM2.5-1.2B-Instruct-abliterated-4bit | 4-bit | 659 MB | 3 GB | 219 |
|---|---|---|---|---|
| Josiefied-LFM2.5-1.2B-Instruct-abliterated-6bit | 6-bit | 951 MB | 4 GB | 27 |
| Josiefied-LFM2.5-1.2B-Instruct-abliterated-8bit | 8-bit | 1.2 GB | 4 GB | 24 |
| Josiefied-LFM2.5-1.2B-Instruct-abliterated-bfloat16 | Unstated | 2.3 GB | 5 GB | 26 |
| Josiefied-LFM2.5-1.2B-Instruct-abliterated-mxfp4 | MXFP4 | 2.3 GB | 5 GB | 24 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.