The story so far
Weights, every dated article, and repo commits on one rail.
16 repo commits since the weights landed
Teal is the weights (2023-06-30), grey ticks are repo commits.
multilingual-e5-small
118M parameters, text in, embeddings out, 512 tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #13 in Embeddings · score 103 method v1 Sources 3 Downloads 30d 9.3M · #11 of 619 tracked
Changed this week: 4 new quantized builds on the Hub (299 in all).2026-10-24 · 3 new quantized builds on the Hub (298 in all).2026-10-24
Do people use it?9.3Mdownloads, 30 days#11 of 619 we track · top 2%+3 likes, downloads −3% this week469 likesHugging Face2026-10-24
Where to run it
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | HF Inference | — | — | — | — | Oct 25 |
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; heavily run locally (299 quantized builds); a big base for builders (214 fine-tunes, adapters and merges).
- As a service1HF Inference
- On own hardware299quantized builds
- Built on214206 fine-tunes · 8 adapters · 0 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: embedl/hfviewer ♥ 181 · radames/Candle-BERT-Semantic-Similarity-Wasm ♥ 17 · antoinelouis/mtem-pruner ♥ 14 · hotchpotch/wikipedia-japanese-rag-qa ♥ 6
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 0.1 GB at INT4, 0.1 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
How it scores
Third-party measurements only; author-reported numbers stay in Reference, marked as such.
#31 of 64 on MTEB so far
59.69. Each tick is a model on this site with a measured MTEB row; author-reported numbers stay in Reference. Mean(task) x100 over 41 tasks. 41 tasks, split=test
Source · leaderboard · 2026-10-24
What people built on it
513 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
513 derivatives on the Hub, most of them quantized
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Benchmarks
39 rows
Benchmarks 39 rows
measured third-party leaderboard row (3)author-reported number from the model card or eval files (36)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| measured MTEB · Embed text for search | 46.43 nDCG@10 x100 (mean of 10 tasks) | 10 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB · Embed text for search | 59.69 mean(task) x100 over 41 tasks | 41 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB Reranking · Rerank search results | 43.19 MAP x100 (mean of 2 tasks) | 2 tasks, split=test | leaderboard | 2026-10-24 |
| author-reported Mr. TyDi · Embed text for search | 64.4 | multilingual-e5-small | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 71.5 | multilingual-e5-small (ar) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 66.3 | multilingual-e5-small (bn) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 54.5 | multilingual-e5-small (en) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 57.7 | multilingual-e5-small (fi) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 63.2 | multilingual-e5-small (id) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 55.4 | multilingual-e5-small (ja) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 54.3 | multilingual-e5-small (ko) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 60.8 | multilingual-e5-small (ru) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 65.4 | multilingual-e5-small (sw) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 89.1 | multilingual-e5-small (te) | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 70.1 | multilingual-e5-small (th) | model author | 2026-10-07 |
| author-reported ArguAna_default_test (mteb/arguana) | 39.09 | Obtained using MTEB v1.36.26 | Obtained using MTEB v1.36.26 | 2026-10-24 |
| author-reported ArguAna (mteb/arguana) | 39.09 | Obtained using MTEB v1.36.26 | Obtained using MTEB v1.36.26 | 2026-10-24 |
| author-reported BrightAopsRetrieval_default_standard (mteb/BRIGHT) | 7.92 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightAopsRetrieval (mteb/BRIGHT) | 7.92 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightBiologyLongRetrieval_default_long (mteb/BRIGHT) | 9.71 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightBiologyLongRetrieval (mteb/BRIGHT) | 9.71 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightBiologyRetrieval_default_standard (mteb/BRIGHT) | 4.24 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightBiologyRetrieval (mteb/BRIGHT) | 4.24 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEarthScienceLongRetrieval_default_long (mteb/BRIGHT) | 14.94 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEarthScienceLongRetrieval (mteb/BRIGHT) | 14.94 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
Show all 39 rows (14 more)
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported BrightEarthScienceRetrieval_default_standard (mteb/BRIGHT) | 19.29 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEarthScienceRetrieval (mteb/BRIGHT) | 19.29 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEconomicsLongRetrieval_default_long (mteb/BRIGHT) | 10.68 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEconomicsLongRetrieval (mteb/BRIGHT) | 10.68 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEconomicsRetrieval_default_standard (mteb/BRIGHT) | 7.41 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightEconomicsRetrieval (mteb/BRIGHT) | 7.41 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightLeetcodeRetrieval_default_standard (mteb/BRIGHT) | 23.58 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightLeetcodeRetrieval (mteb/BRIGHT) | 23.58 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPonyLongRetrieval_default_long (mteb/BRIGHT) | 0.75 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPonyLongRetrieval (mteb/BRIGHT) | 0.75 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPonyRetrieval_default_standard (mteb/BRIGHT) | 0.18 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPonyRetrieval (mteb/BRIGHT) | 0.18 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPsychologyLongRetrieval_default_long (mteb/BRIGHT) | 2.97 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
| author-reported BrightPsychologyLongRetrieval (mteb/BRIGHT) | 2.97 | Obtained using MTEB v2.10.12 | Obtained using MTEB v2.10.12 | 2026-03-31 |
What the card says
1 cited sentence
Use-case evidence
3 use cases
What it is good at 3 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
- Embed text for searchmeasuredMTEB(eng, v2) retrieval 46.43MTEB(eng, v2) 59.69Author reports Mr. TyDi 89.1+5 more
- Work across languagesstructuraldecision-model estimate p=1.00name: multilingualtag: multilingual+1 more
- Run on a laptop or phonestructuraldecision-model estimate p=1.00name: smallfits: edge
Facts
21 fields
Listed in Embeddings
Facts
- multilingual-e5-small has 118M parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 512 tokens (512). (config.json max_position_embeddings, observed 2026-10-24)
- License: MIT (friction: none). Permissive. (license file, observed 2026-10-24)
- Created 2023-06-30, last modified 2026-04-02. (HF API, observed 2026-10-24)
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | BertModel |
| Model type | bert |
| Dtype | float32 |
| Params by dtype | F32: 117,653,760 · I64: 512 |
| Size band | S |
| MoE | no |
| Context length | 512 (config.json max_position_embeddings) |
| Languages | multilingual, af, am, ar, as, az, be, bg, bn, br, bs, ca, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fr, fy, ga, gd, gl, gu, ha, he, hi, hr, hu, hy, id, is, it, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, om, or, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, so, sq, sr, su, sv, sw, ta, te, th, tl, tr, ug, uk, ur, uz, vi, xh, yi, zh |
| Papers | arXiv:2402.05672, arXiv:2108.08787, arXiv:2104.08663, arXiv:2210.07316 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · BertModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · BertModel · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for multilingual-e5-small: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.1 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
All variants
40 variants
Lineage
quantized: 299finetune: 206adapter: 8
Top variants (40 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| Xenova/multilingual-e5-small | quantized | — | — | — | — | Xenova | 21 | 5M |
| HuggingFaceTB/finemath-classifier | finetune | — | 118M | S | mit | HuggingFaceTB | 16 | 188.4k |
| dragonkue/multilingual-e5-small-ko-v2 | finetune | — | 118M | S | apache-2.0 | dragonkue | 5 | 118.3k |
| dragonkue/multilingual-e5-small-ko | finetune | — | 118M | S | apache-2.0 | dragonkue | 11 | 91.9k |
| upskyy/e5-small-korean | finetune | — | 118M | S | mit | upskyy | 2 | 79.2k |
| alphaedge-ai/multilingual-e5-small-fra-32768 | quantized | — | 34.2M | S | mit | alphaedge-ai | 0 | 37.8k |
| gety-ai/gety-embed-v0 | quantized | — | — | — | mit | gety-ai | 3 | 20.4k |
| cstr/multilingual-e5-small-GGUF | quantized | GGUF | — | — | mit | cstr | 1 | 10.7k |
| SergeyKarpenko1/multilingual-e5-small-legal-matryoshka_384 | finetune | — | 118M | S | apache-2.0 | SergeyKarpenko1 | 0 | 9.2k |
| super-cinnamon/fewshot-followup-multi-e5 | finetune | — | 118M | S | — | super-cinnamon | 3 | 6k |
| rhlsinghal1s/german-multilingual-e5-small | quantized | — | 40.0M | S | mit | rhlsinghal1s | 1 | 5.3k |
| antoinelouis/french-me5-small | quantized | — | 35.9M | S | mit | antoinelouis | 0 | 4.8k |
| keisuke-miyako/multilingual-e5-small-gguf-q8_0 | quantized | gguf | — | — | — | keisuke-miyako | 2 | 4.4k |
| kazalbrur/bangla-embed-e5-small-banglish | finetune | — | 118M | S | mit | kazalbrur | 1 | 3.5k |
| slovak-nlp/e5-sk-small | finetune | — | 44.7M | S | mit | slovak-nlp | 0 | 3.3k |
| TwinSunsLLC/multilingual-e5-small-gguf | quantized | gguf | — | — | mit | TwinSunsLLC | 2 | 2.7k |
| thegenerativegeneration/stay_or_go_conversation_classifier_s_v2 | finetune | — | 118M | S | — | thegenerativegeneration | 0 | 2.8k |
| cnmoro/multilingual-e5-small-distilled-16m | finetune | — | 16.0M | S | mit | cnmoro | 2 | 2.7k |
| ferrisS/german-english-multilingual-e5-small | quantized | — | 40.0M | S | mit | ferrisS | 0 | 2.1k |
| agentlans/multilingual-e5-small-domain-classifier | finetune | — | 118M | S | mit | agentlans | 0 | 2k |
| clips/e5-small-trm | finetune | — | 40.8M | S | mit | clips | 0 | 1.9k |
| djovak/embedic-small | finetune | — | 118M | S | mit | djovak | 2 | 1.7k |
| Manav2op/verdict-small | quantized | — | 118M | S | apache-2.0 | Manav2op | 1 | 1.6k |
| Omartificial-Intelligence-Space/E5-all-nli-triplet-Matryoshka | finetune | — | 118M | S | — | Omartificial-Intelligence-Space | 2 | 1.5k |
| jalbarracin/multilingual-e5-small-distilled-256d | finetune | — | 64.0M | S | mit | jalbarracin | 0 | 1.4k |
| kazalbrur/bangla-embed-e5-small | finetune | — | 118M | S | mit | kazalbrur | 0 | 1.1k |
| keisuke-miyako/multilingual-e5-small-gguf-q4_k_m | quantized | gguf | — | — | — | keisuke-miyako | 0 | 1.1k |
| tamikisg/multilingual-e5-small-coreml | quantized | — | — | — | mit | tamikisg | 1 | 1k |
| Yoonyoul/fine-tuned-e5-small-drugproduct | finetune | — | 118M | S | mit | Yoonyoul | 8 | 622 |
| agentlans/multilingual-e5-small-pii-detector | finetune | — | 118M | S | apache-2.0 | agentlans | 8 | 601 |
| LocalDoc/LocRet-small | finetune | — | 118M | S | apache-2.0 | LocalDoc | 2 | 885 |
| alekseevpavel04/multilingual-e5-small-ru-law | finetune | — | 118M | S | mit | alekseevpavel04 | 0 | 955 |
| Yigit-Karaman/turkish_focused-multilingual-e5-small | adapter | — | 118M | S | — | Yigit-Karaman | 1 | 871 |
| keisuke-miyako/multilingual-e5-small-gguf-f16 | quantized | gguf | — | — | — | keisuke-miyako | 0 | 895 |
| Data-Lab/multilingual-e5-small-cross-encoder-v0.1 | finetune | — | 118M | S | — | Data-Lab | 0 | 812 |
| agentlans/multilingual-e5-small-aligned | finetune | — | 118M | S | — | agentlans | 0 | 766 |
| ferrisS/german-multilingual-e5-small | quantized | — | 35.8M | S | mit | ferrisS | 0 | 730 |
| antoinelouis/crossencoder-me5-small-mmarcoFR | finetune | — | 118M | S | mit | antoinelouis | 0 | 706 |
| cnmoro/portuguese-multilingual-e5-small | quantized | — | 39.8M | S | mit | cnmoro | 1 | 620 |
| sukhrobnurali/uzbek-e5-small | finetune | — | 118M | S | mit | sukhrobnurali | 2 | 564 |
Repository changelog
16 commits
Repository changelog 16 commits
| Date | Commit | SHA |
|---|---|---|
| 2026-04-02 | Add evaluation results for model intfloat/multilingual-e5-small revision fd1525a9fd15316a2d503bf26ab031a61d056e98 (#22) | 614241f |
| 2026-04-02 | Add evaluation results for model intfloat/multilingual-e5-small revision fd1525a9fd15316a2d503bf26ab031a61d056e98 (#21) | 99f9015 |
| 2025-02-17 | Add exported openvino model 'openvino_model.xml' (#14) | c007d7e |
| 2025-02-17 | Add exported onnx model 'model_O4.onnx' (#13) | ccc66d3 |
| 2025-02-17 | Add exported onnx model 'model_qint8_avx512_vnni.onnx' (#12) | 6a0d452 |
| 2024-07-29 | add_russian_mteb_scores (#9) | fd1525a |
| 2024-02-15 | Update README.md | 0a68dcd |
| 2024-02-14 | Add link to new paper (#7) | 97e13e8 |
| 2023-09-08 | Adding ONNX file of this model (#4) | ffdcc22 |
| 2023-08-07 | Update README.md | ada7b62 |
| 2023-07-27 | add sentence similarity tag | 475bc35 |
| 2023-07-20 | Update README.md | d829207 |
| 2023-07-12 | change `model_max_length` value to fit positional embeddings number (#2) | 960310a |
| 2023-07-03 | Adding `safetensors` variant of this model (#1) | 7cf867c |
| 2023-06-30 | upload model weights | d2648e2 |
| 2023-06-30 | initial commit | a94d6a0 |
All providers
1 provider · 1 endpoint
Where to run 1 providers · 1 endpoints
Hosted endpoints observed for multilingual-e5-small, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| HF Inference hf | intfloat/multilingual-e5-small | — | — | — | — | — | — | — | live | 2026-10-25 |
Papers
4 papers
Papers 4
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Similar models
3 models
Similar models
- paraphrase-multilingual-MiniLM-L12-v2 · 118M same size band (S), same task (sentence-similarity), permissive license
- all-mpnet-base-v2 · 109M same size band (S), same task (sentence-similarity), more providers, permissive license
- e5-base-v2 · 109M same size band (S), same task (sentence-similarity), more providers, permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:33 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 UTC · Last verified 2026-10-25
Follow multilingual-e5-small
Watch this model
- /feeds/models/intfloat--multilingual-e5-small.xml(RSS 2.0) · every change to multilingual-e5-small
- /feeds/families/intfloat--e5-small.xml(RSS 2.0) · every change across the e5-small family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.