Goekdeniz-Guelmez · First MLX build 29 Sept 2024
Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
MLX
Text apache-2.0
A 7.6B parameter text generation model from Goekdeniz-Guelmez, with 4 MLX builds, from 2-bit to 8-bit.
- Parameters
- 7.6B From Hugging Face
- Quantisation
- 4-bit Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-4-bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.3 GB Weights, estimated
- Downloads
- 314 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 7 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-Qwen2.5-7B-Instruct-abliterated-v2-4-bit --prompt "Hello"MLX builds
4 on mlx-community| Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-2-bit | 2-bit | 2.4 GB | 5 GB | 94 |
|---|---|---|---|---|
| Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-4-bit | 4-bit | 4.3 GB | 7 GB | 314 |
| Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-8-bit | 8-bit | 8.1 GB | 12 GB | 53 |
| Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 | Unstated | 15.2 GB | 20 GB | 206 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.