6-bit Open on Hugging Face
Parameters
596M
Weights (est.)
≈ 484 MB
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/Gabliterated-Qwen3-0.6B-6bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated-Dev (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 18 in the last 30 days · 199 all time · 0 likes
- Published
- 2025-06-28 · updated 2025-06-28 (1y ago)
- Tags
- qwen3, uncensored, code, legal
Other MLX builds of Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated-Dev
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Gabliterated-Qwen3-0.6B-4bit | 4-bit | ≈ 335 MB | 8 GB+ | 30 |
| Gabliterated-Qwen3-0.6B-6bit (this one) | 6-bit | ≈ 484 MB | 8 GB+ | 18 |
| Gabliterated-Qwen3-0.6B-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 21 |
| Gabliterated-Qwen3-0.6B | — | ≈ 1.2 GB | 8 GB+ | 23 |
| Gabliterated-Qwen3-0.6B-float32 | — | ≈ 2.4 GB | 8 GB+ | 21 |