Modelpublic

pipenetwork/LongCat-2.0-4bit

sourceHugging Facemitupdated 3mo agoView on Hugging Face

0likes359downloads

Model Card

pipenetwork/LongCat-2.0-4bit

4-bit MLX quantization (group-size 64, router classifiers @8-bit, MTP dropped) of meituan-longcat/LongCat-2.0 — a 1.6T / ~48B-active MoE. Converted from the FP8 source with mlx-lm.

Requires mlx-lm PR #1464

bash

pip install git+https://github.com/ml-explore/mlx-lm.git@refs/pull/1464/head

python

from mlx_lm import load, generate
model, tok = load("pipenetwork/LongCat-2.0-4bit")
p = tok.apply_chat_template([{"role":"user","content":"Who is Albert Einstein?"}], add_generation_prompt=True)
print(generate(model, tok, prompt=p, max_tokens=512, verbose=True))