Nemotron Shortcut
NVIDIA's Nemotron Shortcut may be coming, a model that appears to read text, images and video, and it is being prepared for developers running it on servers.
Not confirmed yet. The maker hasn't announced this. trckr spotted it via GitHub vllm-project/vllm, which makes it an Early signal: A hint that a model is coming before it's announced: a name spotted in a lab's systems, an anonymous test model, or code that adds support for it. Usually right, sometimes not.: usually right, but details may change or turn out to be wrong.
Key facts
- Released
- Nov 17, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.
Can I use it?
Not officially released yet. Here's what's known so far; trckr updates this page when it launches.
In an app
No app mentioned so far.
For developers
No developer access mentioned so far.
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
The details
An unconfirmed vLLM pull request adds support for a Nemotron Shortcut model from NVIDIA that appears to accept text, image and video inputs and includes a draft head for faster output.
Timeline
/GitHub vllm-project/vllmFirst signal
[Model] Add Nemotron Shortcut (text, MTP, vision-language) (vllm-project/vllm #68198)
Get alerts like this the moment they happen.
From NVIDIA and every other major lab.