{"v":1,"id":"model:hf:ente-ai/embeddinggemma-300m-gguf","slug":"model-ente-ai-embeddinggemma-300m-gguf","kind":"model","category":"embedding","title":"embeddinggemma-300m-gguf","summary":"EmbeddingGemma 300M Q80 GGUF — Ente mirror for Ensu","source":{"provider":"hf","ref":"ente-ai/embeddinggemma-300m-gguf","url":"https://huggingface.co/ente-ai/embeddinggemma-300m-gguf","rev":"957b55764bd672f51240ac026e3a23ac9459ee3c","fetchedAt":"2026-10-02T20:59:15.290Z","etag":"W/\"770-nY6tmSFAXRVbr6GciWhr98jPSzw\""},"author":{"name":"ente-ai","url":"https://huggingface.co/ente-ai"},"license":{"spdx":"gemma","raw":"gemma","open":false,"note":"restricted license: terms at the source apply"},"metrics":{"downloads":22266,"downloadsWeek":327838,"likes":0,"takenAt":"2026-10-02T20:59:15.290Z"},"tags":["gguf","embeddings","on-device","embeddinggemma","feature-extraction","endpoints_compatible"],"pipeline":"feature-extraction","links":{"github":"google-deepmind/gemma","npm":"node-llama-cpp"},"updatedAt":"2026-07-15T09:24:04.000Z","collectedAt":"2026-10-02T20:59:15.290Z","review":{"numbers":["22,266 downloads on Hugging Face","0 likes","license gemma","0.3 GB for embeddinggemma-300M-Q8_0.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:15.290Z","http":200},"description":"# EmbeddingGemma 300M Q8_0 GGUF — Ente mirror for Ensu\n\nThis repository is an **Ente-operated, byte-for-byte mirror** of a single\nupstream GGUF artifact. It exists so that [Ensu](https://ente.io)'s on-device\nretrieval feature can download its shared embedding model directly, while\nremaining exactly compatible with the published Ensu knowledge packs.\n\nEnte has **not** modified, re-converted, re-quantized, or repacked the GGUF\nfile. See [`MODIFICATIONS.md`](./MODIFICATIONS.md) for the modification\ndisclosure and [`PROVENANCE.json`](./PROVENANCE.json) for machine-readable\nprovenance.\n\n## Source\n\n| Field | Value |\n|---|---|\n| Base model | [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) |\n| Source GGUF repository | [ggml-org/embeddinggemma-300M-GGUF](https://huggingface.co/ggml-org/embeddinggemma-300M-GGUF) |\n| Source revision (immutable) | `0f741b5a6585bd53aeb15cd1372c56f2a0f65e12` |\n| Filename | `embeddinggemma-300M-Q8_0.gguf` |\n| SHA-256 | `b5ce9d77a3fc4b3b39ccb5643c36777911cc4eb46a66962eadfa3f5f60490d63` |\n\nThe GGUF Q8_0 artifact is a converted/quantized derivative of\n`google/embeddinggemma-300m`; the conversion was published upstream by\nggml-org.\n\n## Terms of use\n\nThis model is a Gemma model and is provided under and subject to the\n[Gemma Terms of Use](https://ai.google.dev/gemma/terms), including the\nincorporated [Gemma Prohibited Use\nPolicy](https://ai.google.dev/gemma/prohibited_use_policy). By downloading or\nusing this model you agree to be bound by those terms and must not use the\nmodel for any use restricted by the Prohibited Use Policy.\n\nCopies of the required notice, terms, policy, and provenance files are\nincluded in this repository:\n\n- [`NOTICE`](./NOTICE)\n- [`GEMMA_TERMS_OF_USE.txt`](./GEMMA_TERMS_OF_USE.txt)\n- [`GEMMA_PROHIBITED_USE_POLICY.txt`](./GEMMA_PROHIBITED_USE_POLICY.txt)\n- [`MODIFICATIONS.md`](./MODIFICATIONS.md)\n- [`PROVENANCE.json`](./PROVENANCE.j…\n\nSource: https://huggingface.co/ente-ai/embeddinggemma-300m-gguf","install":{"kind":"model","hfId":"ente-ai/embeddinggemma-300m-gguf","gated":false,"format":"gguf","files":[{"name":"embeddinggemma-300M-Q8_0.gguf","size":333590944,"quant":"Q8_0","sha256":"b5ce9d77a3fc4b3b39ccb5643c36777911cc4eb46a66962eadfa3f5f60490d63"}],"totalBytes":333590944,"suggestedFile":"embeddinggemma-300M-Q8_0.gguf","requirements":{"ramGb":1,"diskBytes":333590944,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp"],"command":"lsh models install hf:ente-ai/embeddinggemma-300m-gguf"}}