Parameters
4.0B
Weights (est.)
≈ 8.0 GB
Mac memory (est.)
16 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-r1-4b-bfloat16 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josie-r1-4b
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- —
- Downloads
- 17 in the last 30 days · 73 all time · 0 likes
- Published
- 2025-12-18 · updated 2025-12-18 (10mo ago)
- Tags
- qwen3, chat
Other MLX builds of Goekdeniz-Guelmez/Josie-r1-4b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josie-r1-4b-4bit | 4-bit | ≈ 2.3 GB | 8 GB+ | 17 |
| Josie-r1-4b-6bit | 6-bit | ≈ 3.3 GB | 8 GB+ | 14 |
| Josie-r1-4b-8bit | 8-bit | ≈ 4.3 GB | 8 GB+ | 13 |
| Josie-r1-4b-bfloat16 (this one) | — | ≈ 8.0 GB | 16 GB+ | 17 |