cstr/multilingual-e5-small-gguf - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
cstr/multilingual-e5-small-gguf overview
GGUF format of intfloat/multilingual-e5-small for use with CrispEmbed and Ollama.
Downloads
1,139
Likes
0
Pipeline
feature-extraction
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "mit",
"language": [
"en",
"de",
"fr",
"es",
"zh",
"ja",
"ko",
"ar",
"hi",
"pt",
"ru",
"it",
"nl",
"pl",
"tr",
"vi",
"th",
"id",
"sv",
"da",
"no",
"fi",
"cs",
"ro",
"hu",
"bg",
"uk",
"ca",
"el",
"hr",
"sk",
"sl",
"et",
"lt",
"lv",
"ms",
"tl",
"sw",
"af",
"cy",
"ga",
"sq",
"mk",
"bs",
"mt",
"gl",
"eu",
"is",
"ka",
"hy",
"kk",
"uz",
"az",
"be",
"mn",
"ne",
"si",
"km",
"my",
"lo",
"am",
"ps",
"sd",
"ku",
"ug",
"bo",
"dz",
"fy"
],
"tags": [
"embeddings",
"gguf",
"ggml",
"text-embeddings",
"bert",
"crispembed",
"ollama"
],
"pipeline_tag": "feature-extraction",
"base_model": "intfloat/multilingual-e5-small",
"frontmatter": {
"license": "mit",
"language": "[en, de, fr, es, zh, ja, ko, ar, hi, pt, ru, it, nl, pl, tr, vi, th, id, sv, da, no, fi, cs, ro, hu, bg, uk, ca, el, hr, sk, sl, et, lt, lv, ms, tl, sw, af, cy, ga, sq, mk, bs, mt, gl, eu, is, ka, hy, kk, uz, az, be, mn, ne, si, km, my, lo, am, ps, sd, ku, ug, bo, dz, fy]",
"tags": "[embeddings, gguf, ggml, text-embeddings, bert, crispembed, ollama]",
"pipeline_tag": "feature-extraction",
"base_model": "intfloat/multilingual-e5-small"
},
"hero_image_url": "",
"summary": "GGUF format of intfloat/multilingual-e5-small for use with CrispEmbed and Ollama.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: mit\nlanguage: [en, de, fr, es, zh, ja, ko, ar, hi, pt, ru, it, nl, pl, tr, vi, th, id, sv, da, no, fi, cs, ro, hu, bg, uk, ca, el, hr, sk, sl, et, lt, lv, ms, tl, sw, af, cy, ga, sq, mk, bs, mt, gl, eu, is, ka, hy, kk, uz, az, be, mn, ne, si, km, my, lo, am, ps, sd, ku, ug, bo, dz, fy]\ntags: [embeddings, gguf, ggml, text-embeddings, bert, crispembed, ollama]\npipeline_tag: feature-extraction\nbase_model: intfloat/multilingual-e5-small\n---\n\n# multilingual-e5-small GGUF\n\nGGUF format of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) and [Ollama](https://ollama.com).\n\n## Files\n\n| File | Quantization | Size |\n|------|-------------|------|\n| [multilingual-e5-small-q4_k.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small-q4_k.gguf) | Q4_K | 0 MB |\n| [multilingual-e5-small-q8_0.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small-q8_0.gguf) | Q8_0 | 0 MB |\n| [multilingual-e5-small.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small.gguf) | F32 | 0 MB |\n\n**Recommended:** Q8_0 for quality (cos vs HF: 0.9999), Q4_K for size (0.990).\n\n## Quick Start\n\n### CrispEmbed\n```bash\n./crispembed -m multilingual-e5-small \"Hello world\"\n./crispembed-server -m multilingual-e5-small --port 8080\n```\n\n### Ollama (with [CrispStrobe fork](https://github.com/CrispStrobe/ollama/tree/feat/xlmr-embedding))\n```bash\n# Create model\necho \"FROM multilingual-e5-small-q8_0.gguf\" > Modelfile\nollama create multilingual-e5-small -f Modelfile\n\n# Embed\ncurl http://localhost:11434/api/embed -d '{\"model\":\"multilingual-e5-small\",\"input\":[\"Hello world\"]}'\n```\n\n### Python (CrispEmbed)\n```python\nfrom crispembed import CrispEmbed\nmodel = CrispEmbed(\"multilingual-e5-small-q8_0.gguf\")\nvectors = model.encode([\"Hello world\", \"Goodbye world\"])\n```\n\n## Model Details\n\n| Property | Value |\n|----------|-------|\n| Architecture | BERT |\n| Parameters | 118M |\n| Embedding Dimension | 384 |\n| Layers | 12 |\n| Pooling | mean |\n| Tokenizer | SentencePiece |\n| Language | multilingual |\n| Q8_0 vs HuggingFace | 0.9999 |\n| Q4_K vs HuggingFace | 0.990 |\n\n## Server API\n\nCrispEmbed server supports four API dialects:\n- `POST /embed` — native\n- `POST /v1/embeddings` — OpenAI-compatible\n- `POST /api/embed` — Ollama-compatible\n- `POST /api/embeddings` — Ollama legacy\n\n## Credits\n\n- Original model: [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)\n- Inference: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (MIT, ggml-based)\n",
"related_quantizations": []
},
"tags": [
"gguf",
"embeddings",
"ggml",
"text-embeddings",
"bert",
"crispembed",
"ollama",
"feature-extraction",
"en",
"de",
"fr",
"es",
"zh",
"ja",
"ko",
"ar",
"hi",
"pt",
"ru",
"it",
"nl",
"pl",
"tr",
"vi",
"th",
"id",
"sv",
"da",
"no",
"fi",
"cs",
"ro",
"hu",
"bg",
"uk",
"ca",
"el",
"hr",
"sk",
"sl",
"et",
"lt",
"lv",
"ms",
"tl",
"sw",
"af",
"cy",
"ga",
"sq",
"mk",
"bs",
"mt",
"gl",
"eu",
"is",
"ka",
"hy",
"kk",
"uz",
"az",
"be",
"mn",
"ne",
"si",
"km",
"my",
"lo",
"am",
"ps",
"sd",
"ku",
"ug",
"bo",
"dz",
"fy",
"base_model:intfloat/multilingual-e5-small",
"base_model:quantized:intfloat/multilingual-e5-small",
"license:mit",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 1139,
"gated": false,
"private": false,
"last_modified": "2026-04-16T05:27:23.000Z",
"created_at": "2026-04-15T03:29:04.000Z",
"pipeline_tag": "feature-extraction",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69df060064bf953efc0fa47f",
"id": "cstr/multilingual-e5-small-GGUF",
"modelId": "cstr/multilingual-e5-small-GGUF",
"sha": "98d7a31f1c6144931582f6ad3fedb0c0ef65a5c3",
"createdAt": "2026-04-15T03:29:04.000Z",
"lastModified": "2026-04-16T05:27:23.000Z",
"author": "cstr",
"downloads": 1139,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "feature-extraction",
"library_name": "",
"siblings_count": 5
}