Files
zeekay d016d87d10 Tell the Zen 6 story on the zen-docs overview
The overview called Zen LM "next-generation language models built on
Qwen3 architecture" and sold unsourced claims: 95% less energy than
cloud AI, carbon-negative operations, no API fees. It now says who
makes Zen LM, Zoo Labs Foundation, a 501(c)(3) non-profit, the two jobs
it is chosen for, that Zen 6 and Zen 6 Flash are available now, and
that Zen 7 is a research preview with a link to request access. The
older model pages sit under "Earlier Models".

The site had not built on main: the docs page read page.slug and
page.data.default, which fumadocs no longer has, the untyped loader hid
both from the editor, and "<1 second" in a table parsed as a JSX tag.
All three are fixed, and scripts/check-zen.mjs now runs after the build
and fails it on an upstream name outside data-upstream.

Nothing serves this repository: its Pages deploy has failed on every
run and no DNS name points at it. LLM.md says so.
2026-09-30 07:29:04 -07:00

79 lines
3.1 KiB
Plaintext

---
title: Zen LM Documentation
description: Open models from Zoo Labs Foundation for agentic coding on your own machine and marketing work
---
# Welcome to Zen LM
Zen LM is the open model family of Zoo Labs Foundation, a 501(c)(3) non-profit. It is chosen for two jobs:
- **Agentic coding that runs on your own machine** — long context, tool use and fast decoding.
- **Marketing work** — content, campaigns and brand voice, with the images and video behind them.
## Available now: Zen 6 and Zen 6 Flash
- **Zen 6** — 27B dense; reads text, images and video; 262,144 tokens native, 1,048,576 with YaRN. [Weights](https://huggingface.co/zenlm/zen6) · `zen6` on api.hanzo.ai
- **Zen 6 Flash** — the ternary build of Zen 6: 1.77 bits per weight, 5.95 GB; reads images; runs on an Apple Silicon laptop. [Weights](https://huggingface.co/zenlm/zen6-flash) · `zen6-flash` on api.hanzo.ai
Specifications and serving commands are on [docs.zenlm.org](https://docs.zenlm.org/docs/models/zen6/).
## Research preview: Zen 7
Zen 7 is the next open-weight generation. It has no weights yet and cannot be called. [Request access](https://hanzo.ai/research-access).
## Earlier Models
The models below predate Zen 6; each page links its weights.
### Language Models
- **[zen-nano](/docs/models/zen-nano)** - 0.6B ultra-lightweight edge model
- **[zen-eco](/docs/models/zen-eco)** - 4B efficient model family
- **[zen-agent](/docs/models/zen-agent)** - 4B tool-calling and functions
- **[zen-coder](/docs/models/zen-coder)** - 4B-480B code generation
- **[zen-next](/docs/models/zen-next)** - 80B professional-grade LLM
### Multimodal Models
- **[zen-omni](/docs/models/zen-omni)** - 7B multimodal (text + vision + audio)
- **[zen-vl](/docs/models/zen-vl)** - Vision-language understanding
- **[zen-designer](/docs/models/zen-designer)** - Design and UI generation
### Media Generation
- **[zen-director](/docs/models/zen-director)** - Text/image-to-video
- **[zen-3d](/docs/models/zen-3d)** - 3D asset generation
- **[zen-video](/docs/models/zen-video)** - Video synthesis
- **[zen-musician](/docs/models/zen-musician)** - Music generation
- **[zen-foley](/docs/models/zen-foley)** - Audio effects
### Specialized
- **[zen-guard](/docs/models/zen-guard)** - Content safety
- **[zen-embedding](/docs/models/zen-embedding)** - Text embeddings
- **[zen-scribe](/docs/models/zen-scribe)** - Audio transcription
## Quick Start
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-nano")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-nano")
inputs = tokenizer("Hello, I am", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))
```
## Organizations
- **Zoo Labs Foundation** — 501(c)(3) non-profit, maker of Zen LM • [zoo.ngo](https://zoo.ngo)
- **Hanzo AI** — serves Zen models on [api.hanzo.ai](https://api.hanzo.ai) • [hanzo.ai](https://hanzo.ai)
## Contact
- 🌐 [zenlm.org](https://zenlm.org)
- 💬 [Discord](https://discord.gg/hanzoai)
- 🐦 [Twitter](https://twitter.com/hanzoai)
- 📧 [[email protected]](mailto:[email protected])