Instructions to use kernelpool/LongCat-2.0-3bit-UVMAX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kernelpool/LongCat-2.0-3bit-UVMAX 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("kernelpool/LongCat-2.0-3bit-UVMAX")

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 kernelpool/LongCat-2.0-3bit-UVMAX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "kernelpool/LongCat-2.0-3bit-UVMAX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kernelpool/LongCat-2.0-3bit-UVMAX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use kernelpool/LongCat-2.0-3bit-UVMAX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "kernelpool/LongCat-2.0-3bit-UVMAX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "kernelpool/LongCat-2.0-3bit-UVMAX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "kernelpool/LongCat-2.0-3bit-UVMAX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use kernelpool/LongCat-2.0-3bit-UVMAX 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 "kernelpool/LongCat-2.0-3bit-UVMAX"

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 kernelpool/LongCat-2.0-3bit-UVMAX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kernelpool/LongCat-2.0-3bit-UVMAX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "kernelpool/LongCat-2.0-3bit-UVMAX"

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 "kernelpool/LongCat-2.0-3bit-UVMAX" \
  --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"

kernelpool commited on Jul 4

Commit

ba6849b

verified ·

1 Parent(s): 50438e2

Update README.md

Browse files

Files changed (1) hide show

README.md +25 -1

README.md CHANGED Viewed

@@ -4,14 +4,38 @@ library_name: mlx
 pipeline_tag: text-generation
 tags:
 - mlx
 ---
 # kernelpool/LongCat-2.0-3bit-UVMAX
 ## Use with mlx
 ```bash
-pip install mlx-lm
 ```
 ```python

 pipeline_tag: text-generation
 tags:
 - mlx
+license: mit
+base_model: meituan-longcat/LongCat-2.0-FP8
 ---
 # kernelpool/LongCat-2.0-3bit-UVMAX
+Mixed-precision (UVMAX) quantization of [meituan-longcat/LongCat-2.0-FP8](https://huggingface.co/meituan-longcat/LongCat-2.0-FP8),
+converted with [mlx-lm](https://github.com/ml-explore/mlx-lm).
+## What is UVMAX?
+UVMAX is a mixed-precision scheme: bit widths are assigned per tensor class
+from measured round-trip quantization error, rather than uniformly. All
+classes use group size 64.
+| Tensor class | Bits | Parameters | Size | Share |
+|---|---|---|---|---|
+| Expert FFNs | 3 | 1.47 T | 598.5 GiB | 88.0% |
+| N-gram embedding tables | 3 | 135 B | 55.0 GiB | 8.1% |
+| Attention, dense MLPs | 6 | 31.4 B | 22.9 GiB | 3.4% |
+| Embeddings, `lm_head` | 6 | 2.8 B | 2.1 GiB | 0.3% |
+| DSA indexer, MoE routers | 8 | 0.6 B | 0.6 GiB | 0.1% |
+| Norms, correction biases (unquantized) | — | — | 0.9 GiB | 0.1% |
 ## Use with mlx
+This model requires LongCat-2.0 support from [mlx-lm PR #1464](https://github.com/ml-explore/mlx-lm/pull/1464),
+which has not yet been merged. Until it is included in an mlx-lm release, install
+mlx-lm from the PR branch:
 ```bash
+pip install git+https://github.com/ml-explore/mlx-lm.git@refs/pull/1464/head
 ```
 ```python