google/embeddinggemma-2
28 derivatives checked
- unsloth/embeddinggemma-2-GGUF: Same weights, converted
- ggml-org/embeddinggemma-2-GGUF: Same weights, converted
- ngquocvinh/EmbeddingGemma-2-GGUF: Quantization
- unsloth/embeddinggemma-2: Identical copy
- mlx-community/embeddinggemma-2-bf16: Same weights, repacked
- webmp3/Sakura-EmbeddingGemma-2-HighQuality-GGUF: Quantization
- AtomicChat/embeddinggemma-2-GGUF: Same weights, converted
- prithivMLmods/EmbeddingGemma-2-GGUF: Same weights, converted
- mlx-community/embeddinggemma-2-mxfp8: Quantization
- Fastiraz/embeddinggemma-2-GGUF: Same weights, converted
- mlx-community/embeddinggemma-2-8bit: Quantization
- webmp3/Sakura-EmbeddingGemma-2-AutoRound-GGUF: Quantization
- mlx-community/embeddinggemma-2-mxfp4: Quantization
- mlx-community/embeddinggemma-2-4bit: Quantization
- webmp3/Sakura-Gemma4-E2B-EmbeddingGemma2-DualMode-GGUF: Not comparable yet
- nativ-community/embeddinggemma-2-8bit: Quantization
- mlx-community/embeddinggemma-2-nvfp4: Quantization
- webmp3/Sakura-Gemma4-E4B-EmbeddingGemma2-DualMode-GGUF: Not comparable yet
- jayyun98/embeddinggemma-2-text-image-440m-mlx-fp32: Same weights, converted (fewer layers)
- nativ-community/embeddinggemma-2-bf16: Same weights, repacked
- jayyun98/embeddinggemma-2-text-270m-mlx-fp32: Same weights, converted (fewer layers)
- jayyun98/embeddinggemma-2-text-270m-mlx-bf16: Same weights, repacked (fewer layers)
- gahabeen/embeddinggemma-2-text-270m-mlx-bf16: Same weights, repacked (fewer layers)
- mlx-community/embeddinggemma-2-5bit: Quantization
- empyrealworks/EmbeddingGemma-2-GGUF: Quantization
- mlx-community/embeddinggemma-2-6bit: Quantization
- jayyun98/embeddinggemma-2-text-image-440m-mlx-bf16: Same weights, repacked (fewer layers)
- eulogik/bharat-embed-270m-gemma2: LoRA-style (fewer layers)
12 other repos hold byte-for-byte identical weight files.