Goekdeniz-Guelmez · First MLX build 13 Mar 2026
Josiefied-Qwen3.5-0.8B-gabliterated-v1
MLX
Text
A 752M parameter text generation model from Goekdeniz-Guelmez, with 5 MLX builds, from 4-bit to 8-bit.
- Parameters
- 752M From Hugging Face
- Quantisation
- 4-bit Josiefied-Qwen3.5-0.8B-gabliterated-v1-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 424 MB Weights, estimated
- Downloads
- 60 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-Qwen3.5-0.8B-gabliterated-v1-4bit --prompt "Hello"MLX builds
5 on mlx-community| Josiefied-Qwen3.5-0.8B-gabliterated-v1-4bit | 4-bit | 424 MB | 3 GB | 60 |
|---|---|---|---|---|
| Josiefied-Qwen3.5-0.8B-gabliterated-v1-mxfp4 | MXFP4 | 424 MB | 3 GB | 52 |
| Josiefied-Qwen3.5-0.8B-gabliterated-v1-6bit | 6-bit | 612 MB | 3 GB | 32 |
| Josiefied-Qwen3.5-0.8B-gabliterated-v1-8bit | 8-bit | 800 MB | 3 GB | 38 |
| Josiefied-Qwen3.5-0.8B-gabliterated-v1-bfloat16 | Unstated | 1.5 GB | 4 GB | 51 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.