
NVIDIA published a series of new "Nemotron 3 Super 120B" open-source models on Huggingface, designed for agentic use.

By
–

NVIDIA published a series of new "Nemotron 3 Super 120B" open-source models on Huggingface, designed for agentic use.
By
–
Good! Models capabilities are always going to diffuse, so better to build them open source as part of architecture.
By
–
“We're an American company, but we work with companies across the world,” @ctnzr says. “It's in our interest to make the ecosystem diverse and strong everywhere.” Read more on how we are committed to helping the AI ecosystem develop through our open source models.

By
–

OpenRouter now has 2 new stealth models, Hunter Alpha with a 1M context window for agentic use, and Healer Alpha, an omni-modal model.

By
–
Launching Demo Jam: a new AI demo showcase for the Axelera AI community. If you're working with Metis and Voyager SDK, we want to see what you're building, learning, and figuring out. Record a short demo video, tutorial, post or repo and share it on the community. You you
By
–
Thanks! I think it shouldn't be too hard. I have a Qwen3.5 from-scratch implementation here: https://
github.com/rasbt/LLMs-fro
m-scratch/blob/main/ch05/16_qwen3.5/qwen3.5-plus-kv-cache.ipynb
… that you can use as a drop-in replacement. Perhaps the easiest thing to do here is to take that and put it into the qwen. py (
https://
github.com/rasbt/LLMs-fro
m-scratch/blob/main/pkg/llms_from_scratch/qwen3.py
…). If you

By
–
Day 0 support for Nvidia's Nemotron 3 Super! We're excited to support open source models that push the frontier of model intelligence, cost, and latency Try it out in deepagents today!
By
–
REMINDER: The project and releases are now hosted on Codeberg. Enjoying it very much, easier to customize the Action Runners.
By
–
It is absurd to have a problem with AI learning from code you have open sourced. If github trained models on the contents of your private repos, that would be a violation.