mirror of
https://github.com/zenlm/zen-coder.git
synced 2026-11-10 21:30:01 +00:00
Rewrite dead HF links to live successors, refresh stale Zen4 / old Zen-3 chat lineups to current Zen5 canonical + Zen3 specialty, and refresh user-facing prose (attribution and base_model chains preserved). Co-authored-by: zooqueen <[email protected]>
1.2 KiB
1.2 KiB
zen-coder — AI Knowledge Base
Project: zen-coder Organization: zenlm Repository: https://github.com/zenlm/zen-5-coder-gguf HuggingFace: https://huggingface.co/zenlm/zen-5-coder-gguf Last Updated: 2026-02-27
Overview
zen-coder is the code-focused model family from Zen LM. Models range from 4B (edge) to 480B (MoE frontier). Built on -Coder architecture with extended context (128K tokens).
Model Variants
| Model | Params | Base | Context |
|---|---|---|---|
| zen-coder (4B) | 4B | Qwen3-Coder-4B | 32K |
| zen-coder-flash (31B MoE) | 31B/3B active | GLM-4.7-Flash | 131K |
| zen-coder-480b | 480B/30B active | Qwen3-Coder | 128K |
Rules for AI Assistants
- ALWAYS update LLM.md with significant discoveries
- NEVER commit model weights (*.safetensors, *.bin, *.gguf, *.pt)
- NEVER commit symlinked files (CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md)
- NEVER create random summary files — update THIS file only
- Zen models are based on Qwen3 (not Qwen2!)
Context
This file (LLM.md) is symlinked as CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md.
Part of the Zen AI family — Clarity Through Intelligence