Checked fact 199620 Oct 2026Models and releases

The model card says Nvidia compressed the Nemotron 3.5 Super VL parent checkpoint (120B-A12B) to Nemotron 3.5 Bolt 74B-A9B 24GB using Star Elastic.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

We compress the Nemotron 3.5 Super VL parent checkpoint (120B-A12B) to Nemotron 3.5 Bolt 74B-A9B 24GB using Star Elastic

What the source said when we opened it, on 20 Oct 2026.

The source

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB model card
NVIDIA (Hugging Face) · 2026-10-15

Open the source archived copy

Checked

Checked by the notis newsroom on 20 Oct 2026, against the source above.

In the story

Nvidia released Nemotron 3.5 Bolt, a 74B open-weight vision-language model that fits in 24GB, under the OpenMDW licence. 20 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The model card says Nvidia compressed the Nemotron 3.5 Super VL parent checkpoint (120B-A12B) to Nemotron 3.5 Bolt 74B-A9B 24GB using Star Elastic.” ai notis, checked 20 Oct 2026. Source: NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB model card (NVIDIA (Hugging Face)). https://ainotis.com/c/1996

As a reference (APA style)

ai notis. (2026, October 20). The model card says Nvidia compressed the Nemotron 3.5 Super VL parent checkpoint (120B-A12B) to Nemotron 3.5 Bolt 74B-A9B 24GB using Star Elastic [Checked claim 1996]. ai notis. https://ainotis.com/c/1996

Anyone may quote this address. It does not change; if we correct the story, this page says so.