Views
No views yet
mlx_lm.convert --hf-path meituan-longcat/LongCat-Flash-Thinking-2601 --mlx-path LongCat-Flash-Thinking-2601-MLX-5.5bpw --quantize --q-bits 5
until it crashed with a KeyError;
adding "model_type": "longcat_flash", to the downloaded config.json,
then running the command again.