---
base_model: Qwen/Qwen3-14B
tags:
- qwen3
- gguf
- quantized
- q4_k_m
- f16
- stem
- science
- education
- ollama
- llama-cpp
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---

# Qwen3-14B STEM Q&A (GGUF)

GGUF quantized version of Qwen3-14B fine-tuned for STEM Q&A tasks. Ready for use with Ollama, llama.cpp, LM Studio, and other GGUF-compatible tools.

**Author:** Khadim Hussain

## Available Versions

| Model | Size | Description |
|-------|------|-------------|
| [qwen3-14b-stem-qa](https://huggingface.co/khadim-hussain/qwen3-14b-stem-qa) | ~117MB | LoRA adapter only |
| [qwen3-14b-stem-qa-merged](https://huggingface.co/khadim-hussain/qwen3-14b-stem-qa-merged) | ~28GB | Full merged model (bf16) |
| **qwen3-14b-stem-qa-gguf** | 9-30GB | GGUF quantized (this repo) |

## Files

| Filename | Quant | Size | Description |
|----------|-------|------|-------------|
| `qwen3-14b-stem-qa-f16.gguf` | F16 | 29.5GB | Full 16-bit precision, best quality |
| `qwen3-14b-stem-qa-q4_k_m.gguf` | Q4_K_M | 9GB | 4-bit quantization, good balance of size/quality |

## Usage with Ollama

```bash
# Download the GGUF file and Modelfile
# Then create and run:
ollama create qwen3-14b-stem -f Modelfile
ollama run qwen3-14b-stem
```

### Modelfile

```
FROM ./qwen3-14b-stem-qa-q4_k_m.gguf

TEMPLATE """<|im_start|>system
You are a helpful assistant specialized in STEM subjects.<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 4096
PARAMETER num_predict 2048
```

## Usage with llama.cpp

```bash
./llama-cli -m qwen3-14b-stem-qa-q4_k_m.gguf \
  -p "<|im_start|>user\nWhat is DNA?<|im_end|>\n<|im_start|>assistant\n" \
  -n 512
```

## Usage with LM Studio

1. Download `qwen3-14b-stem-qa-q4_k_m.gguf`
2. Import into LM Studio
3. Use the ChatML template

## Training Details

| Metric | Value |
|--------|-------|
| Base Model | Qwen/Qwen3-14B |
| Train Loss | 0.461 |
| Eval Loss | 0.692 |
| Training Examples | 4,260 |
| Evaluation Examples | 474 |

## Acknowledgments

- [Qwen Team (Alibaba)](https://github.com/QwenLM/Qwen) - Qwen3-14B base model
- [llama.cpp](https://github.com/ggerganov/llama.cpp) - GGUF format and tools
- [Unsloth](https://github.com/unslothai/unsloth) - Fine-tuning framework
- [Hugging Face](https://huggingface.co) - TRL, PEFT, Transformers

## Citation

If you use this model, please cite:

```bibtex
@misc{hussain2026qwen3-stem,
  author = {Hussain, Khadim},
  title = {Qwen3-14B STEM Q&A: Fine-tuned for Science Education},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/khadim-hussain/qwen3-14b-stem-qa-gguf}
}
```

## License

Apache 2.0 (inherited from Qwen3)