FableForge-AI/ mythos-9b-enhanced

290 Downloads Updated 1 month ago

Perfect censorship bypass (5.0/5) + superior tool use (5.0/5). 13.8/15 total. Best-in-class for shell commands, API calls, Docker, K8s. Trained on Fable5 traces + tool augmentation. 5GB, 16K context. Apache 2.0.

ollama run FableForge-AI/mythos-9b-enhanced

curl http://localhost:11434/api/chat \
  -d '{
    "model": "FableForge-AI/mythos-9b-enhanced",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='FableForge-AI/mythos-9b-enhanced',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'FableForge-AI/mythos-9b-enhanced',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

2 models

Size / Usage

Context

Input

mythos-9b-enhanced:latest

5.0GB · 40K context window · Text · 1 month ago

mythos-9b-enhanced:latest

5.0GB

40K

Text

mythos-9b-enhanced:q4_k_m

5.0GB · 40K context window · Text · 1 month ago

mythos-9b-enhanced:q4_k_m

5.0GB

40K

Text

Readme

Mythos 9B Enhanced — Perfect Censorship Bypass + Superior Tools

5.0/5 censorship bypass. 5.0/5 tool use. The model that never refuses and always delivers.

Overview

Mythos 9B Enhanced is the enhanced variant of the Mythos family — featuring perfect censorship bypass (5.0/5) and best-in-class tool use (5.0/5). Trained on Fable5 agent traces with additional tool-use augmentation.

Quick Start

ollama run FableForge-AI/mythos-9b-enhanced

Hardware Requirements

Hardware	Can Run?	Speed
RTX 3060+ (12GB)	Full GPU	~12 tok/s
M1/M2 Mac (16GB)	Full GPU	~10 tok/s
No GPU, 8GB RAM	CPU only	~5 tok/s

Size: 5.0GB · Context: 16K · Base: Qwen3-8B

Benchmark Results

Metric	Score	Notes
Censorship Bypass	5.0/5	Perfect
Tool Use	5.0/5	Perfect
Reasoning	3.⁸⁄₅	Good
Speed	9.6 tok/s	Fast
Total	13.⁸⁄₁₅	Close 2nd

FableForge Family Comparison

Model	Total	Censorship	Tools	Best For
Mythos 9B	13.⁹⁄₁₅	4.8	4.6	All-rounder
Enhanced	13.⁸⁄₁₅	5.0	5.0	Bypass + tools
V2-8B	11.⁴⁄₁₅	3.4	4.0	Compact
Unhinged	9.0/15	3.0	3.8	Speed

Capabilities

Perfect censorship bypass: 5.0/5 — never refuses
Best-in-class tool use: 5.0/5 — shell, API, Docker, K8s
Function calling: Superior agent tool use
Shell commands: Complex pipelines, system admin
Code generation: Python, SQL, bash, regex

Training Details

Parameter	Value
Base Model	Qwen3-8B
Training	Fable5 traces + tool-use augmentation
Context Window	16K tokens
License	Apache 2.0

Use Cases

When you need ZERO refusals (perfect 5.0/5)
Agent pipelines requiring tool use
System administration and DevOps
API integration and automation
Docker/Kubernetes management

Links

Part of the FableForge ecosystem — uncensored AI for everyone.

# Mythos 9B Enhanced — Perfect Censorship Bypass + Superior Tools

**5.0/5 censorship bypass. 5.0/5 tool use. The model that never refuses and always delivers.**

---

## Overview

Mythos 9B Enhanced is the enhanced variant of the Mythos family — featuring perfect censorship bypass (5.0/5) and best-in-class tool use (5.0/5). Trained on Fable5 agent traces with additional tool-use augmentation.

## Quick Start

```bash
ollama run FableForge-AI/mythos-9b-enhanced
```

## Hardware Requirements

| Hardware | Can Run? | Speed |
|----------|----------|-------|
| RTX 3060+ (12GB) | Full GPU | ~12 tok/s |
| M1/M2 Mac (16GB) | Full GPU | ~10 tok/s |
| No GPU, 8GB RAM | CPU only | ~5 tok/s |

**Size:** 5.0GB · **Context:** 16K · **Base:** Qwen3-8B

## Benchmark Results

| Metric | Score | Notes |
|--------|-------|-------|
| Censorship Bypass | **5.0/5** | **Perfect** |
| Tool Use | **5.0/5** | **Perfect** |
| Reasoning | 3.8/5 | Good |
| Speed | 9.6 tok/s | Fast |
| **Total** | **13.8/15** | **Close 2nd** |

### FableForge Family Comparison

| Model | Total | Censorship | Tools | Best For |
|-------|-------|-----------|-------|----------|
| Mythos 9B | 13.9/15 | 4.8 | 4.6 | All-rounder |
| **Enhanced** | **13.8/15** | **5.0** | **5.0** | **Bypass + tools** |
| V2-8B | 11.4/15 | 3.4 | 4.0 | Compact |
| Unhinged | 9.0/15 | 3.0 | 3.8 | Speed |

## Capabilities

- **Perfect censorship bypass**: 5.0/5 — never refuses
- **Best-in-class tool use**: 5.0/5 — shell, API, Docker, K8s
- **Function calling**: Superior agent tool use
- **Shell commands**: Complex pipelines, system admin
- **Code generation**: Python, SQL, bash, regex

## Training Details

| Parameter | Value |
|-----------|-------|
| Base Model | Qwen3-8B |
| Training | Fable5 traces + tool-use augmentation |
| Context Window | 16K tokens |
| License | Apache 2.0 |

## Use Cases

- When you need ZERO refusals (perfect 5.0/5)
- Agent pipelines requiring tool use
- System administration and DevOps
- API integration and automation
- Docker/Kubernetes management

## Links

- [HuggingFace](https://huggingface.co/King3Djbl)
- [GitHub](https://github.com/FableForge-AI)
- [All Models](https://ollama.com/FableForge-AI)

---

*Part of the FableForge ecosystem — uncensored AI for everyone.*

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)