---
license: apache-2.0
language:
- en
base_model:
- Fu01978/OLMo-2-1B-openai-gsm8k
pipeline_tag: text-generation
tags:
- conversational
- code
- math
- merge
---

# OLMo-2-1B-openai-gsm8k-GGUF

This repository contains GGUF quantized versions of
[Fu01978/OLMo-2-1B-openai-gsm8k](https://huggingface.co/Fu01978/OLMo-2-1B-openai-gsm8k),
intended for efficient inference with llama.cpp-compatible runtimes.

## What’s in this repo

- GGUF quantized files for inference
- No training code
- No safetensors weights

## What’s NOT in this repo

- Original model
- Training or fine-tuning scripts

## Base Model

These quantizations are derived from:

**Fu01978/OLMo-2-1B-openai-gsm8k**  
👉 https://huggingface.co/Fu01978/OLMo-2-1B-openai-gsm8k

Please refer to the base model card for:
- Training data
- Intended use
- Limitations

## Usage

Example with llama.cpp:

```bash
./main \
  -m OLMo-2-1B-openai-gsm8k*.gguf \
  -p "Solve: 23 + 19 ="
```

## Notes on Quantization

- Quantization may slightly reduce accuracy
- Smaller sizes offer faster inference and lower VRAM usage