Model Releases

Hugging Face releases fully open-source 3B model SmolLM3 with 128k context and dual-mode reasoning

Original title:SmolLM3: smol, multilingual, long-context reasoner

AI summary

Hugging Face released SmolLM3, a fully open-source 3B model pretrained on 11T tokens. The company said it outperforms Llama-3.2-3B and Qwen2.5-3B at the 3B scale and competes with 4B models such as Qwen3 and Gemma3.

Key Takeaways

  • Hugging Face released SmolLM3,a fully open-source 3B model pretrained on 11T tokens.
  • The company said it outperforms Llama-3.
  • 2-3B and Qwen2.
  • 5-3B at the 3B scale and competes with 4B models such as Qwen3 and Gemma3.

Quick Facts

Published
Updated
Source
Hugging Face 社区博客(混合发现)
Category
Model Releases
AI score
76
Read the original Read the full article at the original source
Why it matters

官方完整公开 3B 模型的架构改动、三阶段数据配比和双模式训练配方,想复现或改进小模型的人可据此省去数月逆向工程。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Hugging Face releases fully open-source 3B model SmolLM3 with 128k context and dual-mode reasoning. July 8, 2025. https://new.nat6.net/en/news/x23efo4mfgbbgww4lwc4c5s95/

View all →