hugpadhugpad

PrimeIntellect / qwen3-moe-tiny

Text Generation670M5K4Updated Feb 18, 2026
Hugging Face

Downloads

5K

Likes

4

Last updated

Feb 18, 2026

License

apache-2.0

A small (~670M parameter) Qwen3 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with prime-rl.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • qwen3_moe
  • text-generation
  • prime-rl
  • moe
  • test-model

Technical specifications

Parameters670M
Librarytransformers
LanguagesNot available
Licenseapache-2.0