4-bit Open on Hugging Face
Parameters
596M
Weights (est.)
≈ 335 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/JOSIE-IT1-Qwen3-0.6B-4bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 28 in the last 30 days · 187 all time · 0 likes
- Published
- 2026-01-12 · updated 2026-01-12 (10mo ago)
- Tags
- qwen3, chat
Other MLX builds of Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| JOSIE-IT1-Qwen3-0.6B-4bit (this one) | 4-bit | ≈ 335 MB | 8 GB+ | 28 |
| JOSIE-IT1-Qwen3-0.6B-6bit | 6-bit | ≈ 484 MB | 8 GB+ | 15 |
| JOSIE-IT1-Qwen3-0.6B-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 14 |
| JOSIE-IT1-Qwen3-0.6B-bfloat16 | — | ≈ 1.2 GB | 8 GB+ | 20 |