Zen LM
Frontier language models from 600M to 480B parameters — edge to cloud. Open weights, Zen architecture.
zenlmGitHub Nov 7, 2026
Counted from GitHub
Forks left out · read from GitHub Nov 7, 2026
- public repositories
- stars
- forks
Counted on Hanzo Forge
Every repository of zenlm, mirrored to the forge: private ones are counted, never named, and each commit is counted once.
- merges in the past year
- repositories, 17 of them private
- of those commits written by our people and agents
Repositories
Zen6 Flash — 27B Ultra-Compact Ternary Vision-Language Model (PQ2_0, DFlash2, Metal & Unified Memory Native)
0
ForgeZen6 Coder — 38B-Class Frontier Agentic MoE (Halogen W4B, GGUF UD-IQ4_XS, AMD Strix Halo Native)
Python0
Forgezen5 MoDE — Mixture of Diverse Experts. 3.1T params, 0.8-100B+ active, complexity-aware routing across 6 model families.
Python0
ForgeTraining framework for Zen Coder models - fine-tune 4B to 1T parameter models on agentic coding data
Python0
ForgeZen Embedding 2: one embedding space for text, code, images, video and audio
1 commit this year0
ForgeReact components for the Zen LM model library — model cards, tables, and browsable catalog
TypeScript0
Forge🎥 Satori: Efficient video generation in latent space using diffusion models with explicit temporal dynamics, enabling high-quality frame coherence and reduced computational overhead.
0
Forge🎹 Mu: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion.
Python0
Forge
zenlm
zenlm on GitHub