---
license: apache-2.0
base_model: build-small-hackathon/MiniCPM4-8B-PaperProf
tags:
  - gguf
  - llama.cpp
  - question-generation
  - education
  - paperprof
language:
  - en
---

# MiniCPM4-8B-PaperProf-GGUF

GGUF quantizations of [build-small-hackathon/MiniCPM4-8B-PaperProf](https://huggingface.co/build-small-hackathon/MiniCPM4-8B-PaperProf),
the fine-tuned exam-question generator behind
[PaperProf](https://huggingface.co/spaces/build-small-hackathon/PaperProf).

| File | Quant | Size | Use |
|---|---|---|---|
| `minicpm4-8b-paperprof-Q4_K_M.gguf` | Q4_K_M | ~4.9 GB | recommended, used by the Space |
| `minicpm4-8b-paperprof-f16.gguf` | F16 | ~16 GB | full precision reference |

## Usage with llama.cpp

```bash
llama-cli -hf build-small-hackathon/MiniCPM4-8B-PaperProf-GGUF -p "your prompt"
```

## Usage with llama-cpp-python

```python
from llama_cpp import Llama
llm = Llama.from_pretrained("build-small-hackathon/MiniCPM4-8B-PaperProf-GGUF", filename="*Q4_K_M.gguf", n_gpu_layers=-1)
```

Built for the Build Small Hackathon, June 2026, by Team PaperProf (EPITA).