# Clef / EmbeddingGemma follow-up, 2026-10-11

Hub author search found Cloudflare/clef, Cloudflare/clef-flash, Cloudflare/clef-omni. Hub searches for clef-CoreAI and embeddinggemma-2-CoreAI, plus internet searches, found one Clef Flash Core AI repository and no EmbeddingGemma 2 Core AI repository. Search is evidence of discoverability, not proof none exists anywhere.

Existing public Clef Flash conversion: https://huggingface.co/mlboydaisuke/clef-flash-CoreAI at 220ac149ed1136465f7d9dac93aaf0dfc55d6b73. Source revision 17f0b0ad64efb65d273590632833508766b2aae6. Compared every source safetensors file's LFS SHA256 with Cloudflare/clef-flash current revision 8b2e5fd17c09fd49bc2880b805d5323ec7ff4ff3: all five match, including joint_head. Assets are .aimodel directories. This check verifies published provenance, not an independent runtime audit. Runtime: https://github.com/john-rocky/coreai-model-zoo/tree/main/apps/ClefFlash

Clef 27B has 12 source shards and exceeds a safe conversion budget on this 64 GiB Mac once compiler copies are included. Clef Omni at 0db1cd2607d76a7bdb2a382f659e7b313079f84b has ~70.5 GB source weights, more than installed RAM. Neither was downloaded or attempted. These are capacity preflight exclusions, not observed converter failures.

The old embeddinggemma-300m-CoreAI repositories are not EmbeddingGemma 2. New source google/embeddinggemma-2 at 914f7f89142e33e77833254d9c9b90c3cef7303b is Apache-2.0, 740M multimodal. Transformers 5.17 lacked support. Installed official upstream commit 536ecc007387a50e77603bb5d92100e9b07514cc (5.19.0.dev0) for conversion and processing.