EmbeddingGemma 2 (Q8_0 GGUF), zstd-compressed
The Q8_0 GGUF files of ggml-org/embeddinggemma-2-GGUF
(revision 6ea3e3a309d12a4779cfda98b8c19800d2d5da71), compressed with zstd, unchanged otherwise:
| File | Compressed | Original | SHA-256 of the original |
|---|---|---|---|
embeddinggemma-2-Q8_0.gguf.zst |
280,577,244 | 309,855,456 | 2188ac1deca4b77dffefd603c2776a9d76d9d74ec01841392982ebb840b09135 |
mmproj-embeddinggemma-2-Q8_0.gguf.zst |
296,191,728 | 554,821,056 | 0531309472a6bc6f4b146c3736eee7795ec9db1903c25490d3c937490cef6dd8 |
Each file was cut into 16 MiB pieces, and each piece was compressed as its own zstd frame (level 19), so that an
interrupted download can be resumed from the start of a piece. Together they form an ordinary .zst file:
zstd -d embeddinggemma-2-Q8_0.gguf.zst
The model is by Google (google/embeddinggemma-2) and is licensed under the Apache License 2.0.
Model tree for biantsh/embeddinggemma-2-GGUF-zstd
Base model
google/embeddinggemma-2 Quantized
ggml-org/embeddinggemma-2-GGUF