Goekdeniz-Guelmez · First MLX build 13 Mar 2026
Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4
MLX
Text
A 4B parameter text generation model from Goekdeniz-Guelmez, with 5 MLX builds, from 4-bit to 8-bit.
- Parameters
- 4B From Hugging Face
- Quantisation
- 6-bit Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-6bit
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 3.3 GB Weights, estimated
- Downloads
- 36 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 6 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/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-6bit --prompt "Hello"MLX builds
5 on mlx-community| Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-4bit | 4-bit | 2.3 GB | 5 GB | 32 |
|---|---|---|---|---|
| Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-mxfp4 | MXFP4 | 2.3 GB | 5 GB | 28 |
| Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-6bit | 6-bit | 3.3 GB | 6 GB | 36 |
| Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-8bit | 8-bit | 4.3 GB | 7 GB | 34 |
| Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-bfloat16 | Unstated | 8.0 GB | 11 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.