Goekdeniz-Guelmez · First MLX build 20 Dec 2024
Josiefied-Qwen2.5-3B-Instruct-abliterated-v1
MLX
Text apache-2.0
A 3.1B parameter text generation model from Goekdeniz-Guelmez, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 3.1B From Hugging Face
- Quantisation
- 4-bit Josiefied-Qwen2.5-3B-Instruct-abliterated-v1-4-bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.7 GB Weights, estimated
- Downloads
- 728 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 4 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-Qwen2.5-3B-Instruct-abliterated-v1-4-bit --prompt "Hello"MLX builds
3 on mlx-community| Josiefied-Qwen2.5-3B-Instruct-abliterated-v1-4-bit | 4-bit | 1.7 GB | 4 GB | 728 |
|---|---|---|---|---|
| Josiefied-Qwen2.5-3B-Instruct-abliterated-v1-8-bit | 8-bit | 3.3 GB | 6 GB | 85 |
| Josiefied-Qwen2.5-3B-Instruct-abliterated-v1 | Unstated | 6.2 GB | 9 GB | 46 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.