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

# kernelpool/LongCat-2.0-3bit-UVMAX

Mixed-precision (UVMAX) quantization of [meituan-longcat/LongCat-2.0](https://huggingface.co/meituan-longcat/LongCat-2.0),
converted with [mlx-lm](https://github.com/ml-explore/mlx-lm).

> **Revision note**: originally converted from the FP8 release
> ([meituan-longcat/LongCat-2.0-FP8](https://huggingface.co/meituan-longcat/LongCat-2.0-FP8)),
> the current revision is re-converted from the bf16 master checkpoint.

## 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
from mlx_lm import load, generate

model, tokenizer = load("kernelpool/LongCat-2.0-3bit-UVMAX")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```