---
license: mit
library_name: llama.cpp
base_model: WeiboAI/VibeThinker-3B
tags:
  - gguf
  - llama.cpp
  - ollama
  - qwen2
---

# VibeThinker-3B-GGUF

GGUF quantization of WeiboAI/VibeThinker-3B.

## Base Model

https://huggingface.co/WeiboAI/VibeThinker-3B

## Quantization

- Q4_K_M

## Usage

### Ollama

```bash
ollama run hf.co/madrasmic/VibeThinker-3B-GGUF:Q4_K_M
```

### llama.cpp

```bash
llama-cli -hf madrasmic/VibeThinker-3B-GGUF:Q4_K_M
```