Zen 3 Vision

Parameters: 30B | Architecture: Zen 3 Architecture | Context: 131K | License: Apache 2.0 | Released: 2024-11-01

Zen 3 generation label. Weights at zenlm/zen-vl-30b-instruct.

The Zen 3 family (Q3–Q4 2024) introduced sparse MoE routing and expanded to vision, audio, and multimodal reasoning.

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-vl-30b-instruct", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-vl-30b-instruct")

ollama run hf.co/zenlm/zen-vl-30b-instruct

The Zen LM Family

Joint research collaboration:

Hanzo AI (Techstars '17) — AI infrastructure, API gateway, inference optimization
Zoo Labs Foundation (501c3) — Open AI research, ZIPs governance, decentralized training
Lux Partners Limited — Compute coordination and settlement layer

All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.

HuggingFace · Chat free · API · Docs

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for zenlm/zen-3-vision

Unable to build the model tree, the base model loops to the model itself. Learn more.