MLX-Optimized-Models
Collection
6 items • Updated
GPT4All-J — MLX MXFP4
Quantized to MXFP4 format.
Converted from nomic-ai/gpt4all-j using mlx-lm.
Requirements
The gptj model type is support in lastest mlx-lm offical repo(ml-explore/mlx-lm).
Update at: 2026/09/01
pip install git+https://github.com/ml-explore/mlx-lm.git@f8f0f874ff24110a59389a4e5af701b2b7f44eb1
Use
mlx_lm.generate --model AlphaOxO/GPT4All-J-MXFP4-mlx --prompt "hello"
- Downloads last month
- 112
Model size
6B params
Tensor type
F32
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for AlphaOxO/GPT4All-J-MXFP4-mlx
Base model
nomic-ai/gpt4all-j