EmbeddingGemma 2 is Google DeepMind's open embedding model that maps text, code, images, video and audio into one shared space, so you can search across them from a single query. At 740M parameters it runs on-device, needing about 567MB of RAM on a Pixel 11 Pro for the full multimodal model (191MB for text only). Apache 2.0 licensed, with weights on Hugging Face and Kaggle. MTEB Code score rises from 68.76 to 78.68.
EmbeddingGemma 2 is Google DeepMind's open, lightweight multimodal embedding model. It maps text, code, images, video and audio into one shared space and is small enough to run on a phone.
Problem: Searching by meaning usually needs a pipeline of separate models: a captioning model for images, speech-to-text for audio, a text embedder on top. That's slow, memory-hungry, and often sends your data to the cloud. For private, on-device apps, that's a hard trade-off.
Solution: One 740M-parameter model, built on the Gemma 4 architecture, that embeds all five types of content in the same space. A text query can find a photo, and a voice memo can find a video clip. Everything runs locally, so your data never has to leave the device.
What makes it different: It's modular. You can load only the encoders you need, as little as 270M parameters for text and code, plus optional vision (170M) and audio (300M) encoders. With quantization on a Pixel 11 Pro, it needs about 191MB of RAM for text only and about 567MB for the full multimodal model. It shares its tokenizer and audio encoder with Gemma 4, so running both together uses less memory than running them separately.
Key features:
Text, code, images, video and audio in a single embedding space
8K token context (4x EmbeddingGemma 1), enough for about 5.5 minutes of audio, 29 images or 58 video frames
Vectors can be shrunk from 768 to 512, 256 or 128 dimensions for up to 6x less storage
Code retrieval improves from 68.76 to 78.68 on MTEB Code (+9.92 points)
Google says it leads sub-1B multimodal embedding models on benchmarks like MTEB Code and MAEB (audio)
Can also act as a zero-shot, on-device decision engine: Google's MediaPipe demo scores 500 options per turn in a chess game in under 100 ms
Works with transformers, sentence-transformers, MLX, vLLM, llama.cpp, SGLang, Ollama, LMStudio, Qdrant and Unsloth
Who it's for: Developers building private, offline-capable search, RAG, media retrieval or local codebase search, and anyone who wants cross-modal search without a cloud dependency.
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified →@rohanrecommends
Love that EmbeddingGemma 2 maps text, images, audio and video into one shared embedding space so a single query can pull the right result from any of them.
Congrats on the launch! An open multimodal embedding model this light makes local retrieval much easier to ship. Which device sizes are you targeting for on-device use?
About Google EmbeddingGemma 2 on Product Hunt
“An open, lightweight multimodal embedding model”
Google EmbeddingGemma 2 launched on Product Hunt on October 12th, 2026 and earned 248 upvotes and 3 comments, earning #1 Product of the Day. EmbeddingGemma 2 is Google DeepMind's open embedding model that maps text, code, images, video and audio into one shared space, so you can search across them from a single query. At 740M parameters it runs on-device, needing about 567MB of RAM on a Pixel 11 Pro for the full multimodal model (191MB for text only). Apache 2.0 licensed, with weights on Hugging Face and Kaggle. MTEB Code score rises from 68.76 to 78.68.
Google EmbeddingGemma 2 was featured in Artificial Intelligence (480.8k followers), Audio (2.2k followers) and Video (2k followers) on Product Hunt. Together, these topics include over 139k products, making this a competitive space to launch in.
Who hunted Google EmbeddingGemma 2?
Google EmbeddingGemma 2 was hunted by Rohan Chaubey. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Google EmbeddingGemma 2 stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Rohan Chaubey
EmbeddingGemma 2 is Google DeepMind's open, lightweight multimodal embedding model. It maps text, code, images, video and audio into one shared space and is small enough to run on a phone.
Problem: Searching by meaning usually needs a pipeline of separate models: a captioning model for images, speech-to-text for audio, a text embedder on top. That's slow, memory-hungry, and often sends your data to the cloud. For private, on-device apps, that's a hard trade-off.
Solution: One 740M-parameter model, built on the Gemma 4 architecture, that embeds all five types of content in the same space. A text query can find a photo, and a voice memo can find a video clip. Everything runs locally, so your data never has to leave the device.
What makes it different: It's modular. You can load only the encoders you need, as little as 270M parameters for text and code, plus optional vision (170M) and audio (300M) encoders. With quantization on a Pixel 11 Pro, it needs about 191MB of RAM for text only and about 567MB for the full multimodal model. It shares its tokenizer and audio encoder with Gemma 4, so running both together uses less memory than running them separately.
Key features:
Text, code, images, video and audio in a single embedding space
8K token context (4x EmbeddingGemma 1), enough for about 5.5 minutes of audio, 29 images or 58 video frames
Vectors can be shrunk from 768 to 512, 256 or 128 dimensions for up to 6x less storage
Code retrieval improves from 68.76 to 78.68 on MTEB Code (+9.92 points)
Google says it leads sub-1B multimodal embedding models on benchmarks like MTEB Code and MAEB (audio)
Can also act as a zero-shot, on-device decision engine: Google's MediaPipe demo scores 500 options per turn in a chess game in under 100 ms
Works with transformers, sentence-transformers, MLX, vLLM, llama.cpp, SGLang, Ollama, LMStudio, Qdrant and Unsloth
Who it's for: Developers building private, offline-capable search, RAG, media retrieval or local codebase search, and anyone who wants cross-modal search without a cloud dependency.
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified → @rohanrecommends