Open models

Take · Paired with EmbeddingGemma 2 from 10-07, on-device semantic search now has both the model and the engine. Products like AI Cloud Drive can trial local embedding on the web via WebGPU and keep privacy-sensitive files on the user's device; projects still on the TFLite GPU delegate should schedule a migration.

Take · The 0.8B is less than a point behind the 4B, which makes it attractive for document parsing in AI Cloud Drive: I'll run a comparison on the scans and table-heavy PDFs users upload most, to see whether some parsing can move from a cloud API onto our own machines.

Take · Yes-or-no calls like moderation, routing or whether to hand off to a human don't need a generative model every time. I'll try d1-3B on PandaClaws' pre-publish compliance checks, but only as an evaluation until the license is clear.

Take · Most teams won't run a 550B model; the part worth taking is the method: on IOI 2025 the Nano model (30B total, 3B active) went from 280 after SFT to 468 with test-time strategies like GenCorrect. If you build coding products, try a generate-then-self-correct layer on your own eval set first.

Take · At $1.36 in and $4.18 out, it's worth running PandaClaws' long-form generation and multilingual rewriting against it. But this is a preview with no weights or license yet, so I'd benchmark it on my own eval set through the API now and only weigh self-hosting once the weights and license terms land at month end.

Take · This one maps straight onto my AI Cloud Drive: with images, video, recordings and documents in one vector space, a single query can search across file types without a separate model per format. I'd swap the 270M text version in against my current embedder first, then load the vision module as needed; truncating to 128 dimensions cuts index storage, but measure the recall loss on your own retrieval set first.

Take · About 3B active per token, one GPU, Apache 2.0: this is the shape of model that suits privately deployed long-document Q&A like my AI Cloud Drive. But it only covers German and English, so don't drop it into Chinese workloads; what I want from it is a real throughput number for sliding-window attention plus long context on my own hardware before choosing the next self-hosted model.

Take · Retrieve-then-write-a-cited-answer is the most common request in my AI Cloud Drive's document Q&A. An 8B model that does it in one call means private deployment and a much lower bill. I'll compare citation accuracy on my own documents before replacing the large-model call.