voyage-4-nano-oQ8
This model was quantized using oQ (oMLX v0.3.8) mixed-precision quantization.
Quantization details
- Model type: qwen3
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 69
Model size
97.5M params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for gn00029914/voyage-4-nano-oQ8
Base model
voyageai/voyage-4-nano