jayyun98/embeddinggemma-2-text-270m-mlx-fp32

Same weights, converted (fewer layers) vs google/embeddinggemma-2. jayyun98/embeddinggemma-2-text-270m-mlx-fp32 matches part of google/embeddinggemma-2 (413 of its 1376 tensors; the rest of google/embeddinggemma-2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F32).

Tensors changed: Embeddings 0/2, Norms 0/170, other 0/73, MLP 0/72, Attention 0/96

On the Hub · Downloads on Model Pulse