README.md

metadata

title: README
colorFrom: indigo
colorTo: blue
sdk: static
pinned: false

Vertex Research

Open weights, no matter what.

Why

Open weight model releases have been comming less often and delay. Such as, GLM 5.3 was released via api only for a while, then they released the weights. Same for lots of other models such as Kimi K3, MiniMax M2.7/M3, Deepseek V4 Flash Vision Experimental, Qwen 3.8 2.4T-A95B and so on. There are many smaller groups comming up these days, such as Supra Labs or BananaMind that are releasing better and better SLM's. We intend to be one of them.

What we do

• Train compact language models from scratch and release every usable artifact: base, instruct, and reasoning variants, plus GGUF quantizations for llama.cpp.
• Keep everything Apache 2.0. No gated downloads, no acceptance forms, no API-only releases.

Models

Model	Parameters
Vertex 0.6 5M	5M
Vertex 0.6 15M Chat	15M
Vertex 0.6 100M V2	100M
Vertex 0.6 100M	100M
Vertex 0.6 35M	35M
Vertex 0.1 10M	10M

More sizes and versions are on the way. Follow the org to stay updated.

In training

• Vertex 0.6 200M

---

Vertex Research: small models, sharp edges, weights you keep.