zenlm

Zen — open model family and training stack.

Overview Repositories

87

Projects Packages Code

Zen

An open model family and the training stack behind it.

Models	Open weights across sizes and modalities
Training	Pretraining, fine-tuning, and evaluation pipelines
Serving	Quantization and inference for local and hosted use

Start here

• Site — zenlm.org
• Papers — papers.zenlm.org
• Blog — blog.zenlm.org

Filter

Clear Filter

Archived Not Archived

Forked Not Forked

Mirrored Not Mirrored

Template Not Template

Private Public

Sort

Newest Oldest Alphabetically Reverse alphabetically Most recently updated Least recently updated Most stars Fewest stars Most forks Fewest forks Smallest size Largest size

zen-3d

SVG 0 0 0

Zen 3D — controllable image-to-3D asset generation (WIP; permissive: Pixal3D/TRELLIS MIT)

Updated 2026-06-29 04:02:17 +00:00

zen-video

SVG 0 0 0

Zen Video — text-to-video generation (WIP; permissive: Wan2.2 Apache-2.0)

Updated 2026-06-29 04:02:15 +00:00

zen-video-i2v

SVG 0 0 0

Zen Video I2V — image-to-video generation (WIP; permissive: Wan2.2 Apache-2.0)

Updated 2026-06-29 04:02:12 +00:00

llama.cpp

SVG 0 0 0

Fork of llama.cpp

Updated 2026-06-29 04:01:23 +00:00

zen-logo

TypeScript 0 0 0

Official Zen AI logo package with React components and utilities

Updated 2026-06-29 04:00:44 +00:00

zen-translator

Python 0 0 0

Real-time multimodal translation with voice cloning and lip synchronization

Updated 2026-06-29 04:00:21 +00:00

zen-voyager

SVG 0 0 0

Zen Voyager — explorable, navigable world generation (WIP; permissive: Wan2.2 + TRELLIS)

Updated 2026-06-29 04:00:10 +00:00

zen-world

SVG 0 0 0

Zen World — 3D world & scene generation (WIP; permissive: Wan2.2 + TRELLIS)

Updated 2026-06-29 04:00:07 +00:00

zen4-ultra-trainer

Python 0 0 0

QLoRA training for Zen4 Ultra (1.04T MoE) — gate/router unfreezing approach for MoE uncensoring

Updated 2026-06-27 01:45:32 +00:00

zen4-ultra

0 0 0

Zen4 Ultra — frontier scale language model

Updated 2026-06-27 01:45:25 +00:00

zen4-pro-max

Markdown 0 0 0

Zen4 Pro Max — 80B MoE abliterated foundation model

Updated 2026-06-27 01:45:18 +00:00

zen4-pro

Markdown 0 0 0

Zen4 Pro — 80B MoE professional language model

Updated 2026-06-27 01:45:11 +00:00

zen4-mini

Markdown 0 0 0

Zen4 Mini 8B — fast inference language model

Updated 2026-06-27 01:45:04 +00:00

zen4-max-pro

0 0 0

Zen4 Max Pro — 397B MoE optimized for production

Updated 2026-06-27 01:44:57 +00:00

zen4-max

Markdown 0 0 0

Zen4 Max — 397B MoE frontier reasoning model

Updated 2026-06-27 01:44:50 +00:00