---
language: en
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
base_model:
- Maincode/Maincoder-1B
---

# Maincoder-1B — MLX 8bits

Quantized to 8bits format.

Converted from [Maincode/Maincoder-1B](Maincode/Maincoder-1B) using mlx-lm.

## Requirements

The `Maincoder` model type is support in my mlx-lm fork([AlphaKure/mlx-lm](https://github.com/AlphaKure/mlx-lm/issues/4)).

Update at: 2026/09/09

```bash
pip install git+https://github.com/AlphaKure/mlx-lm.git@19ed84b1e3333bc9c320109b15dec38fe0784d29
```

## Use

* use --extra-eos-token '<|im_end|>'  to avoid loop response

```bash
mlx_lm.generate --model AlphaOxO/Maincoder-1B-8bits-mlx --prompt "def insert_sort(nums: list[int]):" --max-tokens 2048 --extra-eos-token '<|im_end|>'
```