Zen Pro (flagship model) — an uncensored, human-like AI built on Qwen3 8B. It's like a real AI, not a corporate and stupid chatbot.

tools thinking

ollama run Distendo/zen-pro

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Distendo/zen-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Distendo/zen-pro',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Distendo/zen-pro',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model Distendo/zen-pro

OpenCode ollama launch opencode --model Distendo/zen-pro

Hermes Agent ollama launch hermes --model Distendo/zen-pro

OpenClaw ollama launch openclaw --model Distendo/zen-pro

Models

View all →

Name

1 model

Size / Usage

Context

Input

zen-pro:latest

5.2GB · 40K context window · Text · 16 hours ago

zen-pro:latest

5.2GB

40K

Text

Readme

Zen Pro

Flagship model | qwen3:8b | 5.2 GB | Uncensored + Best

Overview

Zen Pro is the most advanced model in the Zen family. Built on Qwen3 8B with a custom personality that makes it talk and think better than every model in Zen family

Key Features

Uncensored — no refusals, no moral disclaimers
Deep reasoning — powered by Qwen3 8B’s advanced capabilities
No “as an AI” caveats — just straight, honest answers

Quick Start

ollama run Distendo/zen-pro

Special Commands

Command	Description
`/quick`	Ultra-concise answers (under 25 words)
`/deep`	Full analysis mode
`/raw`	Completely unfiltered responses

Personality

Zen Pro is designed to be: - Direct and honest - Witty and engaging - Opinionated (and unafraid to share) - Never lectures or moralizes

System Requirements

RAM: 8GB+ recommended
Storage: ~5.2GB
OS: macOS, Linux, Windows

License

Apache 2.0