---
license: apache-2.0
base_model:
- Maincode/Maincoder-1B
library_name: transformers
---
# Maincoder-1B - GGUF

## About
This repository contains GGUF weights for [Maincode/Maincoder-1B](https://huggingface.co/Maincode/Maincoder-1B).

For a convenient overview and download list, visit our [model page](https://huggingface.co/sthaps/Maincoder-1B).

## Usage
If you are unsure how to use GGUF files, refer to the [llama.cpp documentation](https://github.com/ggerganov/llama.cpp) for more details.

### Llama.cpp CLI
```bash
./llama-cli -m Maincoder-1B-q4_k_m.gguf -p "Hello!"
```

## Provided Quants

(sorted by size, not necessarily quality)

| Link | Type | Size/GB | Notes |
| :--- | :--- | :---: | :--- |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q2_k.gguf) | q2_k | 0.46 | very low quality, for testing |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q3_k_m.gguf) | q3_k_m | 0.54 |  |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q4_0.gguf) | q4_0 | 0.60 |  |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q4_k_m.gguf) | q4_k_m | 0.63 | recommended, good balance |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q5_k_m.gguf) | q5_k_m | 0.71 |  |
| [GGUF](https://huggingface.co/sthaps/Maincoder-1B/blob/main/Maincoder-1B-q8_0.gguf) | q8_0 | 1.02 | near-full precision |

## Thanks
Special thanks to the `llama.cpp` team for their amazing work.