{"v":1,"id":"model:hf:nomic-ai/nomic-embed-text-v2-moe-GGUF","slug":"model-nomic-ai-nomic-embed-text-v2-moe-gguf","kind":"model","category":"embedding","title":"nomic-embed-text-v2-moe-GGUF","summary":"Llama.cpp Quantizations of nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings","source":{"provider":"hf","ref":"nomic-ai/nomic-embed-text-v2-moe-GGUF","url":"https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe-GGUF","rev":"ffbcf4c99e5d617dda10ec8c0e9f75754b0cbb80","fetchedAt":"2026-10-02T20:53:36.255Z","etag":"W/\"17ab-/VI4z7izduJsg6BwlMWvtwps+Rs\""},"author":{"name":"nomic-ai","url":"https://huggingface.co/nomic-ai"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":41740,"downloadsWeek":4402710,"likes":80,"takenAt":"2026-10-02T20:53:36.255Z"},"tags":["gguf","sentence-similarity","feature-extraction","en","es","fr","de","it","pt","pl","nl","tr","ja","vi","ru","id","ar","cs","ro","sv","el","uk","zh","hu","da","no","hi","fi","bg","ko","sk","th","he","ca","lt","fa","ms","sl","lv","mr"],"pipeline":"sentence-similarity","links":{"github":"nomic-ai/nomic","npm":"@huggingface/transformers"},"updatedAt":"2025-05-15T00:35:53.000Z","collectedAt":"2026-10-02T20:53:36.255Z","review":{"numbers":["41,740 downloads on Hugging Face","80 likes","license apache-2.0","0.3 GB for nomic-embed-text-v2-moe.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":"2026-10-02T20:53:36.255Z","http":200},"description":"# Llama.cpp Quantizations of nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings\n\n[Blog](https://www.nomic.ai/blog/posts/nomic-embed-text-v2) | [Technical Report](https://huggingface.co/papers/2502.07972) | [AWS SageMaker](https://aws.amazon.com/marketplace/seller-profile?id=seller-tpqidcj54zawi) | [Atlas Embedding and Unstructured Data Analytics Platform](https://atlas.nomic.ai)\n\nThis model was presented in the paper [Training Sparse Mixture Of Experts Text Embedding Models](https://huggingface.co/papers/2502.07972).\n\nUsing llama.cpp commit e3a9421b7 for quantization.\n\nOriginal model: [nomic-embed-text-v2-moe](https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe)\n\n## Usage\n\nThis model can be used with the [llama.cpp server](https://github.com/ggml-org/llama.cpp/blob/master/examples/embedding#post-v1embeddings-openai-compatible-embeddings-api) and other software that supports llama.cpp embedding models.\n\nEmbedding text with `nomic-embed-text` requires task instruction prefixes at the beginning of each string.\n\nFor example, the code below shows how to use the `search_query` prefix to embed user questions, e.g. in a RAG application.\n\nStart a llama.cpp server:\n```\nllama-server -m nomic-embed-text-v2-moe.bf16.gguf --embeddings\n```\n\nAnd run this code:\n```python\nimport requests\n\ndef dot(va, vb):\n    return sum(a * b for a, b in zip(va, vb))\n\ndef embed(texts):\n    resp = requests.post('http://localhost:8080/v1/embeddings', json={'input': texts}).json()\n    return [d['embedding'] for d in resp['data']]\n\ndocs = ['嵌入很酷', '骆驼很酷']  # 'embeddings are cool', 'llamas are cool'\ndocs_embed = embed(['search_document: ' + d for d in docs])\n\nquery = '跟我讲讲嵌入'  # 'tell me about embeddings'\nquery_embed = embed(['search_query: ' + query])[0]\nprint(f'query: {query!r}')\nfor d, e in zip(docs, docs_embed):\n    print(f'similarity {dot(query_embed, e):.2f}: {d!r}')\n```\n\nYou should see output similar to…\n\nSource: https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe-GGUF","install":{"kind":"model","hfId":"nomic-ai/nomic-embed-text-v2-moe-GGUF","gated":false,"format":"gguf","files":[{"name":"nomic-embed-text-v2-moe.Q2_K.gguf","size":273286112,"quant":"Q2_K","sha256":"11843331c8f0d14dca2be4809e1146a3a0411892e33b78ae6971b3f619f8e78b"},{"name":"nomic-embed-text-v2-moe.Q3_K_L.gguf","size":322223072,"quant":"Q3_K_L","sha256":"0be98ccfafd74dd15d4c737f76744f06ac045eddf021fddbc256b60856ddfeef"},{"name":"nomic-embed-text-v2-moe.Q3_K_M.gguf","size":308122592,"quant":"Q3_K_M","sha256":"3444c50a7044f0e7b898896e745eab21a0e313a45a71d8aee6df3fde1d0c3d25"},{"name":"nomic-embed-text-v2-moe.Q3_K_S.gguf","size":288381920,"quant":"Q3_K_S","sha256":"e6ae830aa61bd0684c30f1b57aba5559e48b1d40dd7266a93717ff1deda4861a"},{"name":"nomic-embed-text-v2-moe.Q4_0.gguf","size":324158432,"quant":"Q4_0","sha256":"c15fd36aa079618c10037d9ea3b37237d8a4147b9fc4f8325f32539437d38ae7"},{"name":"nomic-embed-text-v2-moe.Q4_1.gguf","size":341853152,"quant":"Q4_1","sha256":"971f584a5739a1c4f0ab6e4395d72059d5c6c8b0f4815c4b56e49136ef340db4"},{"name":"nomic-embed-text-v2-moe.Q4_K_M.gguf","size":344120288,"quant":"Q4_K_M","sha256":"b5fb2811647b8ef461519a68a3bf67014a84a66a130c8a2af9413ff9f06d3f22"},{"name":"nomic-embed-text-v2-moe.Q4_K_S.gguf","size":325338080,"quant":"Q4_K_S","sha256":"db0608a87a2daf4a52b74912dd678ca6122db26d971bdfcf16d3b11b77047663"},{"name":"nomic-embed-text-v2-moe.Q5_K_M.gguf","size":370828256,"quant":"Q5_K_M","sha256":"a6546bdf4e46288c93d79e6292bbdd8efa7ca87c242a8e60afa9cbacdc641471"},{"name":"nomic-embed-text-v2-moe.Q5_K_S.gguf","size":359547872,"quant":"Q5_K_S","sha256":"540055ed857b6f23521d2fca1a17d31a0e0d0f21aa8e628d48c3e56ef2c20344"},{"name":"nomic-embed-text-v2-moe.Q6_K.gguf","size":397149152,"quant":"Q6_K","sha256":"e74dafe6932fc7ae53f98061401f5cae136203a6b09fa940a2f1eb0ab5804ed8"},{"name":"nomic-embed-text-v2-moe.Q8_0.gguf","size":512225120,"quant":"Q8_0","sha256":"06e7a7e594a26985523c18383aba4aad39fe6e14f08ffc6ab5b554e1ccdc3cff"},{"name":"nomic-embed-text-v2-moe.bf16.gguf","size":957680480,"quant":"BF16","sha256":"94c6c2cc3b9212cb9f11067c4d7fa17319dc54c47a488384ddcee4e3163ca807"},{"name":"nomic-embed-text-v2-moe.f16.gguf","size":957680480,"quant":"F16","sha256":"a5db3381f2e514d3490a3a31fe70eb1a65e95016c85c6c2c23223b810806594f"},{"name":"nomic-embed-text-v2-moe.f32.gguf","size":1907985280,"quant":"F32","sha256":"7c9a85afd70f95e953f36d91c3b7f3d7dda72e3840f63b6ab66fc1856b47506f"}],"totalBytes":7990580288,"suggestedFile":"nomic-embed-text-v2-moe.Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":344120288,"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:nomic-ai/nomic-embed-text-v2-moe-GGUF"}}