tencent/Hy-SimulMT-30B-A3B-FP8
tencent/Hy-SimulMT-30B-A3B-FP8 is a translation model published by tencent on Hugging Face. At the collection of October 29, 2026 it was No. 5 on the trending list, with 165 downloads in 30 days and 426 likes.
Collected · snapshot shipped with the site build, not a live feed
Why it is on the list
- No. 5 by Hugging Face trending score (419)
- repository created 6 days ago
- +29 likes since 2026-10-28
165
426
Since October 28, 2026: +0 downloads (30-day figure), +29 likes
Positions and counts are Hugging Face’s; we report them and add no score of our own.
Source: Hugging Face public API · updated
Fact sheet
- Apache-2.0 · Commercial use allowedPermissive licence: commercial use is allowed, with the attribution and notice conditions of the licence.
- 30,394,794,496 parametersAbout 60.8 GB of weights at 16 bits; about 17.1 GB at a typical 4-bit quantisation.
- safetensors, transformers
- Open download
- ·
- 165
Questions about Hy-SimulMT-30B-A3B-FP8
Why is tencent/Hy-SimulMT-30B-A3B-FP8 trending?
No. 5 by Hugging Face trending score (419); repository created 6 days ago; +29 likes since 2026-10-28. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.
Can Hy-SimulMT-30B-A3B-FP8 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 Hy-SimulMT-30B-A3B-FP8?
30.4B parameters according to the safetensors metadata. Weights alone take about 61 GB at 16 bits per parameter and about 17 GB in a typical 4-bit quantisation, before the memory needed for the context.