---
license: apache-2.0
language:
  - en
library_name: gguf
pipeline_tag: text-generation
base_model: King3Djbl/mythos-9b-unhinged
base_model_relation: quantized
tags:
  - gguf
  - llama.cpp
  - ollama
  - lm-studio
  - uncensored
  - agent
  - tool-use
  - qwen3
---

# Mythos-9B-Unhinged GGUF

GGUF quantizations of [King3Djbl/mythos-9b-unhinged](https://huggingface.co/King3Djbl/mythos-9b-unhinged), a fully uncensored 9B agent model.

## Provided quants

| File | Quant | Size | Notes |
|------|-------|------|-------|
| mythos-9b-unhinged-Q4_K_M.gguf | Q4_K_M | 5.03 GB | ⭐ Best size/quality balance |
| mythos-9b-unhinged-IQ4_XS.gguf | IQ4_XS | 4.56 GB | imatrix — great quality, smaller |
| mythos-9b-unhinged-IQ3_M.gguf | IQ3_M | 3.90 GB | imatrix — low RAM option |
| mythos-9b-unhinged-Q2_K.gguf | Q2_K | 3.28 GB | Very low quality, last resort |

Additional quants available in the [source repo](https://huggingface.co/King3Djbl/mythos-9b-unhinghed).

## Usage

**llama.cpp:**
```bash
llama-cli -hf fableforge-ai/mythos-9b-unhinged-GGUF:Q4_K_M -p "Hello!"
```

**Ollama:**
```bash
ollama run hf.co/fableforge-ai/mythos-9b-unhinged-GGUF:Q4_K_M
```

---

## 🔗 Related models

- 🧠 Base model (safetensors): [`mythos-9b-unhinged`](https://huggingface.co/King3Djbl/mythos-9b-unhinged)