Josiefied-Qwen3-4B-abliterated-v1-6bit
mlx-community/Josiefied-Qwen3-4B-abliterated-v1-6bit
Text generation · mlx
6-bit Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 3.3 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Josiefied-Qwen3-4B-abliterated-v1-6bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1 (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- —
- Downloads
- 63 in the last 30 days · 935 all time · 2 likes
- Published
- 2025-05-01 · updated 2025-05-01 (1y ago)
- Tags
- qwen3, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Qwen3-4B-abliterated-v1-4bit | 4-bit | ≈ 2.3 GB | 8 GB+ | 4.1K |
| Josiefied-Qwen3-4B-abliterated-v1-6bit (this one) | 6-bit | ≈ 3.3 GB | 8 GB+ | 63 |
| Josiefied-Qwen3-4B-abliterated-v1-8bit | 8-bit | ≈ 4.3 GB | 8 GB+ | 40 |
| Josiefied-Qwen3-4B-abliterated-v1-bf16 | bf16 | ≈ 8.0 GB | 16 GB+ | 58 |