---
base_model: swiss-ai/Apertus-8B-Instruct-2509
tags:
- gguf
- apertus
- coding
- sft
---

# apertus-8b-coding-gguf

GGUF conversion of [Colby/apertus-8b-coding](https://huggingface.co/Colby/apertus-8b-coding),
a LoRA fine-tune of [swiss-ai/Apertus-8B-Instruct-2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509)
for coding assistance.

## Quantizations

| File | Format | Size |
|------|--------|------|
| apertus-8b-coding-f16.gguf | FP16 | ~16 GB |
| apertus-8b-coding-q8_0.gguf | Q8_0 | ~8 GB |
| apertus-8b-coding-q5_k_m.gguf | Q5_K_M | ~5 GB |
| apertus-8b-coding-q4_k_m.gguf | Q4_K_M | ~4 GB |

## Ollama usage

```bash
hf download Colby/apertus-8b-coding-gguf apertus-8b-coding-q4_k_m.gguf
ollama create apertus-coding:8b -f Modelfile   # FROM ./apertus-8b-coding-q4_k_m.gguf
ollama run apertus-coding:8b
```