Qwen3-Embedding vs EmbeddingGemma 2: which should you use?

Qwen3-Embedding is text and code in three sizes; EmbeddingGemma 2 puts text, images, audio and video in one space. Compare context, size and licenses.

  • Updated

Verdict. Choose by what you need to search. Qwen3-Embedding handles text and code in three sizes (0.6B, 4B, 8B), reads passages of up to 32,000 tokens and covers more than 100 languages. EmbeddingGemma 2 is a 740M model that puts text, images, audio and video in one shared space, with an 8,192-token context. Both are Apache 2.0. Vectors from different models are not interchangeable, so switching later means re-indexing your data.

Specifications

Specifications Qwen3-EmbeddingEmbeddingGemma 2
DeveloperAlibaba QwenGoogle DeepMind
ReleasedJune 5, 2025October 6, 2026
Total parameters7.57B (Embedding-8B)740M (Full multimodal (740M))
Active parametersAllAll
ArchitectureEncoderEncoder
Context window32K tokens8K tokens
InputTextText, Image, Audio, Video
License Apache 2.0 (Permissive) Apache 2.0 (Permissive)
Memory for the smallest variant (4-bit)1.38 GB (Embedding-0.6B)0.621 GB (Text and code only (270M of the same weights))

Performance claims come from the developer and have not been independently verified.

Pick Qwen3-Embedding if

  • Your data is text or code, and you want to trade accuracy against cost: the 8B model is the most accurate, and the 0.6B model runs on small servers.
  • Your documents are long: it reads up to 32,000 tokens, against 8,192 for EmbeddingGemma 2.
  • You want two-stage search with the matching Qwen3-Reranker models.
  • You need more than 100 languages, including programming languages.

Pick EmbeddingGemma 2 if

  • You need cross-modal search, such as finding a video clip from a voice memo or a photo from a sentence.
  • You want to run on a phone or laptop: the full model is a download of about 1.5 GB.
  • You want small vector storage: it can truncate vectors to 256 or 128 dimensions.
  • Your documents are short, or you are happy to split them into chunks that fit 8,192 tokens.

Qwen3-Embedding · EmbeddingGemma 2