Skip to content

Trending AI Today

InternScience/Sage-A1.5

Model · Text generation · edition of October 26, 2026

InternScience/Sage-A1.5 is a text generation model published by InternScience on Hugging Face. At the collection of October 26, 2026 it was No. 11 on the trending list, with 3,875 downloads in 30 days and 294 likes.

Collected · snapshot shipped with the site build, not a live feed

Why it is on the list

  • No. 11 by Hugging Face trending score (288)
  • repository created 10 days ago
  • +3 likes since 2026-10-25

3,875downloads in 30 days

294likes

Since October 25, 2026: +0 downloads (30-day figure), +3 likes

Positions and counts are Hugging Face’s; we report them and add no score of our own.

Open on Hugging Face (opens in a new tab)

Source: Hugging Face public API · updated

Fact sheet

Licence
Apache-2.0 · Commercial use allowedPermissive licence: commercial use is allowed, with the attribution and notice conditions of the licence.
Size
35,951,822,704 parametersAbout 71.9 GB of weights at 16 bits; about 20.2 GB at a typical 4-bit quantisation.
Formats and library
safetensors, transformers
Access
Open download
Created · last changed
·
Downloads, all time
3,875

Most downloaded quantisations

Repositories that declare this model as base

Questions about Sage-A1.5

Why is InternScience/Sage-A1.5 trending?

No. 11 by Hugging Face trending score (288); repository created 10 days ago; +3 likes since 2026-10-25. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.

Can Sage-A1.5 be used commercially?

The repository is tagged with the licence "Apache-2.0". Permissive licence: commercial use is allowed, with the attribution and notice conditions of the licence. The tag is set by the uploader, so confirm it against the licence file in the repository.

How large is Sage-A1.5?

36B parameters according to the safetensors metadata. Weights alone take about 72 GB at 16 bits per parameter and about 20 GB in a typical 4-bit quantisation, before the memory needed for the context.

Are there quantised versions of Sage-A1.5?

Yes. The most downloaded repositories that declare InternScience/Sage-A1.5 as their base are InternScience/Sage-A1.5-Q4_K_M-GGUF (32K downloads in 30 days), na0x2c6/Sage-A1.5-GGUF (9,401 downloads in 30 days), InternScience/Sage-A1.5-F16-GGUF (7,040 downloads in 30 days).