{"v":1,"id":"model:hf:ChristianAzinn/bge-small-en-v1.5-gguf","slug":"model-christianazinn-bge-small-en-v1-5-gguf","kind":"model","category":"embedding","title":"bge-small-en-v1.5-gguf","summary":"More details please refer to our Github: FlagEmbedding.","source":{"provider":"hf","ref":"ChristianAzinn/bge-small-en-v1.5-gguf","url":"https://huggingface.co/ChristianAzinn/bge-small-en-v1.5-gguf","rev":"7ff89debbd66b77c92ca3346c812cecf229b7e88","fetchedAt":"2026-10-02T21:00:23.531Z","etag":"W/\"135b-vHs8YXen7kLaWucvSAgd9CSxMAo\""},"author":{"name":"ChristianAzinn","url":"https://huggingface.co/ChristianAzinn"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":1873,"downloadsWeek":4402710,"likes":2,"takenAt":"2026-10-02T21:00:23.531Z"},"tags":["sentence-transformers","gguf","feature-extraction","sentence-similarity","transformers","mteb","bert","en"],"pipeline":"feature-extraction","links":{"github":"FlagOpen/FlagEmbedding","npm":"@huggingface/transformers"},"updatedAt":"2024-04-07T22:25:32.000Z","collectedAt":"2026-10-02T21:00:23.531Z","review":{"numbers":["1,873 downloads on Hugging Face","2 likes","license mit","0.0 GB for bge-small-en-v1.5.Q4_K_M.gguf","4,402,710 npm downloads a week for @huggingface/transformers","latest @huggingface/transformers@4.3.0"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:23.531Z","http":200},"description":"# bge-small-en-v1.5-gguf\n\nModel creator: [BAAI](https://huggingface.co/BAAI)\n\nOriginal model: [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)\n\n## Original Description\n\nMore details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).\n\nIf you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using [bge-m3](https://huggingface.co/BAAI/bge-m3).\n\n## Description\n\nThis repo contains GGUF format files for the bge-small-en-v1.5 embedding model.\n\nThese files were converted and quantized with llama.cpp [PR 5500](https://github.com/ggerganov/llama.cpp/pull/5500), commit [34aa045de](https://github.com/ggerganov/llama.cpp/pull/5500/commits/34aa045de44271ff7ad42858c75739303b8dc6eb), on a consumer RTX 4090.\n\nThis model supports up to 512 tokens of context.\n\n## Compatibility\n\nThese files are compatible with [llama.cpp](https://github.com/ggerganov/llama.cpp) as of commit [4524290e8](https://github.com/ggerganov/llama.cpp/commit/4524290e87b8e107cc2b56e1251751546f4b9051), as well as [LM Studio](https://lmstudio.ai/) as of version 0.2.19.\n\n# Meta-information\n## Explanation of quantisation methods\n\n  Click to see details\nThe methods available are:\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_…\n\nSource: https://huggingface.co/ChristianAzinn/bge-small-en-v1.5-gguf","install":{"kind":"model","hfId":"ChristianAzinn/bge-small-en-v1.5-gguf","gated":false,"format":"gguf","files":[{"name":"bge-small-en-v1.5.Q2_K.gguf","size":25250080,"quant":"Q2_K","sha256":"737ca5d6a4e6140749f260e75ed4d3c8ade7ca12fd870f41bee25ed5d7ec0933"},{"name":"bge-small-en-v1.5.Q3_K_L.gguf","size":27738400,"quant":"Q3_K_L","sha256":"d3734409b76ddf8aaa81e6d1d2b7bbec9fa365dde850bebcefbb2026cee1325e"},{"name":"bge-small-en-v1.5.Q3_K_M.gguf","size":26724640,"quant":"Q3_K_M","sha256":"27e8a81326a1aa0d78bc357f095762c04dba087aede7e5bcf9d4ef45f6eedbbb"},{"name":"bge-small-en-v1.5.Q3_K_S.gguf","size":25250080,"quant":"Q3_K_S","sha256":"99f4aa341c90e72b8c8df1e5295161377fe9d73e72cb3495985d61be26a227d1"},{"name":"bge-small-en-v1.5.Q4_0.gguf","size":26190112,"quant":"Q4_0","sha256":"78d56660ce47bcab821e4cc79ceac4f42796d27c563f0562e9e0c7914174b56e"},{"name":"bge-small-en-v1.5.Q4_K_M.gguf","size":29203744,"quant":"Q4_K_M","sha256":"d8c2e0e38bce043562bbc6f437c638c2538bfe02cadfe6476a01f906bfde6d40"},{"name":"bge-small-en-v1.5.Q4_K_S.gguf","size":28217632,"quant":"Q4_K_S","sha256":"b82bc0b52f7273456ecf931d4fd0b6d917d41c1fc456b6b38cb1ea427a27b31a"},{"name":"bge-small-en-v1.5.Q5_0.gguf","size":28844320,"quant":"Q5_0","sha256":"10362cb216ba5afb74b9f17c57c63a11e7756b8299659f3f2bd405b15f4b1983"},{"name":"bge-small-en-v1.5.Q5_K_M.gguf","size":30475552,"quant":"Q5_K_M","sha256":"57f08f3e03e87282b4ece8eb4b90e18bd4aeebfcb57aa7f73901acabd5a5a583"},{"name":"bge-small-en-v1.5.Q5_K_S.gguf","size":29729056,"quant":"Q5_K_S","sha256":"764a40d2817e72ab5b9cf8a60ed7efea39ba51783a9a64d050f23bd9bdb7fca5"},{"name":"bge-small-en-v1.5.Q6_K.gguf","size":35092768,"quant":"Q6_K","sha256":"986233d4edcdd1251431e9164bb0a032407f949030a93d8f98bfa9e6a8a91fe9"},{"name":"bge-small-en-v1.5.Q8_0.gguf","size":36806944,"quant":"Q8_0","sha256":"ec38e8da142596baa913124ae50550de284b6916bf59577ef2f0cb9660c2f514"},{"name":"bge-small-en-v1.5_fp16.gguf","size":67308128,"sha256":"f0b2fef971e8366438bfd2d9aefea1b0115919389448806d290237f638bae999"},{"name":"bge-small-en-v1.5_fp32.gguf","size":133609568,"sha256":"bf40c42ad7d89382e9ba7376d5c4b73f6b556cb541fab37aaa1da9c320149b65"}],"totalBytes":550441024,"suggestedFile":"bge-small-en-v1.5.Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":29203744,"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:ChristianAzinn/bge-small-en-v1.5-gguf"}}