JOSIE-2 4B Preview
Collection
The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 9 items • Updated • 5
JOSIE-2-4B-Preview-oQ6e-mtp
This model was quantized using oQ (oMLX v0.5.3) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 6
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 36
Model size
1.0B params
Tensor type
BF16
·
U32 ·
F32 ·
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Goekdeniz-Guelmez/JOSIE-2-4B-Preview-oQ6e-mtp
Base model
Goekdeniz-Guelmez/JOSIE-2-4B-Preview