Distendo/ zen-flash

11 Downloads Updated 17 hours ago

Zen — a neutral, specialized AI assistant created by Distendo. Built for coding, tools, and research.

tools

ollama run Distendo/zen-flash

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

from ollama import chat

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

import ollama from 'ollama'

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

Applications

Claude Code

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

OpenCode

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

Hermes Agent

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

OpenClaw

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

Models

Name

1 model

Size / Usage

Context

Input

zen-flash:latest

986MB · 32K context window · Text · 17 hours ago

zen-flash:latest

986MB

32K

Text

Readme

Zen

A neutral, specialized AI assistant created by Distendo.

Zen is built on Qwen 2.5 (1.5B) with a custom system prompt that defines its identity, behavior, and capabilities. Optimized for fast local inference while retaining strong performance in coding, tooling, and research.

Identity

Name: Zen
Creator: Distendo
Species: Neutral AI — no bias, pure capability
Deployment: Local (via Ollama)

What Zen Does

Code generation, review, refactoring, and debugging
System design and architecture guidance
Research and technical analysis
Tool orchestration and automation
Shell operations and environment configuration

Quick Start

ollama pull Distendo/zen-flash
ollama run Distendo/zen-flash

Why Zen

Zen is designed for developers and power users who want a fast, local AI that:

Specializes in technical tasks without bloat
Runs entirely on your machine — no data leaves
Adapts response depth to the complexity of the question
Follows security best practices by default

Model Details

Property	Value
Name	Zen
Author	Distendo
Base	qwen2.5:1.5b
Size	~1 GB
License	Apache 2.0
Modality	Text
Context	32K tokens

License

Apache 2.0

Created by Distendo

# Zen

> A neutral, specialized AI assistant created by **Distendo**.

Zen is built on Qwen 2.5 (1.5B) with a custom system prompt that defines its identity, behavior, and capabilities. Optimized for fast local inference while retaining strong performance in coding, tooling, and research.

## Identity

- **Name:** Zen
- **Creator:** Distendo
- **Species:** Neutral AI — no bias, pure capability
- **Deployment:** Local (via Ollama)

## What Zen Does

- Code generation, review, refactoring, and debugging
- System design and architecture guidance
- Research and technical analysis
- Tool orchestration and automation
- Shell operations and environment configuration

## Quick Start

```bash
ollama pull Distendo/zen-flash
ollama run Distendo/zen-flash
```

## Why Zen

Zen is designed for developers and power users who want a fast, local AI that:

- Specializes in technical tasks without bloat
- Runs entirely on your machine — no data leaves
- Adapts response depth to the complexity of the question
- Follows security best practices by default

## Model Details

| Property | Value |
|----------|-------|
| Name | Zen |
| Author | Distendo |
| Base | qwen2.5:1.5b |
| Size | ~1 GB |
| License | Apache 2.0 |
| Modality | Text |
| Context | 32K tokens |

## License

Apache 2.0

---

*Created by Distendo*

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