---
language:
- id
license: apache-2.0
library_name: gguf
pipeline_tag: text-generation
base_model: AksaraLLM/Kiel-Pro-0.5B-v3
tags:
- gguf
- llama.cpp
- ollama
- indonesian
- aksarallm
- qwen2
---
# Kiel-Pro-0.5B-v3-GGUF

GGUF quantizations of [`AksaraLLM/Kiel-Pro-0.5B-v3`](https://huggingface.co/AksaraLLM/Kiel-Pro-0.5B-v3) for inference with [llama.cpp](https://github.com/ggml-org/llama.cpp), [Ollama](https://ollama.ai), [LM Studio](https://lmstudio.ai), and other GGUF runtimes.

## Files

| File | Quant | Size | Recommended use |
|---|---|---|---|
| `Kiel-Pro-0.5B-v3.f16.gguf` | F16 | 0.99 GB | lossless from safetensors |
| `Kiel-Pro-0.5B-v3.q8_0.gguf` | Q8_0 | 0.53 GB | near-lossless, ~2× smaller |
| `Kiel-Pro-0.5B-v3.q6_k.gguf` | Q6_K | 0.51 GB | high quality, ~2.5× smaller |
| `Kiel-Pro-0.5B-v3.q5_k_m.gguf` | Q5_K_M | 0.42 GB | good quality, ~3× smaller |
| `Kiel-Pro-0.5B-v3.q4_k_m.gguf` | Q4_K_M | 0.40 GB | recommended default, ~4× smaller |

## CPU benchmark (AMD EPYC 7763, 2 threads, AVX2)

| Quant | Prompt eval (32 tok) | Generation (16 tok) |
|---|---:|---:|
| `q4_k_m` | **36.7 tok/s** | **20.1 tok/s** |

So a 494M model at q4_k_m runs comfortably on a CPU laptop. Larger quants (q5_k_m, q6_k, q8_0) trade a bit of speed for better quality.

## Quick start — llama.cpp

```bash
huggingface-cli download AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Kiel-Pro-0.5B-v3.q4_k_m.gguf --local-dir .
./llama-cli -m Kiel-Pro-0.5B-v3.q4_k_m.gguf -p "Indonesia adalah" -n 64
```

## Quick start — Ollama

```bash
huggingface-cli download AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Kiel-Pro-0.5B-v3.q4_k_m.gguf Modelfile --local-dir .
ollama create aksara-kiel-pro-0.5b-v3 -f Modelfile
ollama run aksara-kiel-pro-0.5b-v3 "Apa ibukota Indonesia?"
```

## Source model

See [`AksaraLLM/Kiel-Pro-0.5B-v3`](https://huggingface.co/AksaraLLM/Kiel-Pro-0.5B-v3) for architecture, training data, eval results, and limitations.

## Conversion provenance

- Converted with [`convert_hf_to_gguf.py`](https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf.py) from llama.cpp
- Quantized with `llama-quantize` from the same build
- Architecture detected as `qwen2`
- All files listed above are reproducible from the source HF safetensors