---
base_model: openai/gpt-oss-20b
tags:
- gguf
- llama.cpp
- quantized
- gpt-oss
- semanticwiki
datasets:
- GhostScientist/semanticwiki-data
---

# gpt-oss-20b-semanticwiki GGUF

GGUF conversion of [GhostScientist/gpt-oss-20b-semanticwiki](https://huggingface.co/GhostScientist/gpt-oss-20b-semanticwiki), fine-tuned on SemanticWiki data.

## Available Quantizations

| File | Quant | Description |
|------|-------|-------------|
| gpt-oss-20b-semanticwiki-f16.gguf | F16 | Full precision |
| gpt-oss-20b-semanticwiki-q8_0.gguf | Q8_0 | 8-bit (recommended for 32GB+ RAM) |
| gpt-oss-20b-semanticwiki-q5_k_m.gguf | Q5_K_M | 5-bit medium |
| gpt-oss-20b-semanticwiki-q4_k_m.gguf | Q4_K_M | 4-bit medium (smallest) |

## Usage

### With Ollama
```bash
huggingface-cli download GhostScientist/gpt-oss-20b-semanticwiki-gguf gpt-oss-20b-semanticwiki-q8_0.gguf
echo "FROM ./gpt-oss-20b-semanticwiki-q8_0.gguf" > Modelfile
ollama create gpt-oss-semanticwiki -f Modelfile
ollama run gpt-oss-semanticwiki
```

### With llama.cpp
```bash
./llama-cli -m gpt-oss-20b-semanticwiki-q8_0.gguf -p "Your prompt"
```

## Model Details

- **Base Model:** openai/gpt-oss-20b (22B params, 3.6B active - MoE)
- **Fine-tuned Model:** GhostScientist/gpt-oss-20b-semanticwiki
- **Dataset:** GhostScientist/semanticwiki-data
- **Training:** SFT with LoRA using TRL