Instructions to use pipenetwork/LongCat-2.0-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/LongCat-2.0-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pipenetwork/LongCat-2.0-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pipenetwork/LongCat-2.0-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pipenetwork/LongCat-2.0-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/LongCat-2.0-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default pipenetwork/LongCat-2.0-4bit

Run Hermes

hermes

OpenClaw new

How to use pipenetwork/LongCat-2.0-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-4bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "pipenetwork/LongCat-2.0-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use pipenetwork/LongCat-2.0-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/LongCat-2.0-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/LongCat-2.0-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/LongCat-2.0-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LongCat-2.0-4bit / README.md

pipenetwork

Add files using upload-large-folder tool

b4eb211 verified 11 days ago

preview code

Raw

History Blame Contribute Delete

816 Bytes

metadata

language: en
library_name: mlx
pipeline_tag: text-generation
tags:
  - mlx
  - longcat
license: mit
base_model: meituan-longcat/LongCat-2.0-FP8

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

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

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))