Nex-N2-mini MLX-VLM Quantized
Collection
5 items • Updated • 2
Nex-N2-mini-MLX-VLM-4bit
Native MLX-VLM 4-bit quantized version of nex-agi/Nex-N2-mini.
Summary
- Base model:
nex-agi/Nex-N2-mini - Format: native MLX / MLX-VLM
- Quantization: 4-bit MLX-VLM quantization
- Vision: supported
- MTP: not included
- Target runtime: MLX-VLM / oMLX / Apple Silicon
This version is intended as the general stable release. It is compatible with direct mlx-vlm.generate loading.
Quick test
python3 -m mlx_vlm.generate \
--model joowon-jang/Nex-N2-mini-MLX-VLM-4bit \
--image /path/to/image.jpg \
--prompt "Describe this image in one sentence." \
--max-tokens 128 \
--temp 0.0
Notes
For oMLX Native MTP speculative decoding, use:
joowon-jang/Nex-N2-mini-MLX-VLM-4bit-MTP
License
Apache-2.0, following the base model license.
- Downloads last month
- 99
Model size
6B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for joowon-jang/Nex-N2-mini-MLX-VLM-4bit
Base model
nex-agi/Nex-N2-mini