Up to date
278M parameters, text in, embeddings out, 514 tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #20 in Embeddings · score 98.6 method v1 Sources 3 Downloads 30d 5.6M · #27 of 619 tracked
Changed this week: 4 new quantized builds on the Hub (276 in all).2026-10-24
Picked by rule from 31 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
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 |
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 (276 quantized builds); a big base for builders (183 fine-tunes, adapters and merges).
Top Spaces running it: embedl/hfviewer ♥ 181 · antoinelouis/mtem-pruner ♥ 14 · hotchpotch/wikipedia-japanese-rag-qa ♥ 6 · kaengreg/rusBEIR ♥ 6
Weights only, an estimate: leave room for the KV cache. Method
About 0.2 GB at INT4, 0.3 GB at FP8, 0.7 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Third-party measurements only; author-reported numbers stay in Reference, marked as such.
61. 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
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-05-19), amber triangles are 8 dated articles (each links to it), grey ticks are repo commits.
459 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| measured MTEB · Embed text for search | 48.97 nDCG@10 x100 (mean of 10 tasks) | 10 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB · Embed text for search | 61 mean(task) x100 over 41 tasks | 41 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB Reranking · Rerank search results | 44.28 MAP x100 (mean of 2 tasks) | 2 tasks, split=test | leaderboard | 2026-10-24 |
| author-reported Mr. TyDi · Embed text for search | 65.9 | Avg MRR@10 | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 72.3 | ar | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 65 | bn | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 58.5 | en | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 60.8 | fi | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 64.9 | id | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 56.6 | ja | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 55.8 | ko | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 62.7 | ru | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 69 | sw | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 86.6 | te | model author | 2026-10-07 |
| author-reported Mr. TyDi · Embed text for search | 72.7 | th | model author | 2026-10-07 |
| author-reported ArguAna_default_test (mteb/arguana) | 44.21 | Obtained using MTEB v1.12.75 | Obtained using MTEB v1.12.75 | 2026-10-24 |
| author-reported ArguAna (mteb/arguana) | 44.21 | Obtained using MTEB v1.12.75 | Obtained using MTEB v1.12.75 | 2026-10-24 |
The architecture consists of 12 layers and an embedding size of 768.[1] Released under an MIT license, the model supports 100 languages.[2][3]
Generated 2026-10-07 15:01 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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.
Listed in Embeddings
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | XLMRobertaModel |
| Model type | xlm-roberta |
| Dtype | float32 |
| Params by dtype | F32: 278,043,648 · I64: 514 |
| Size band | S |
| MoE | no |
| Context length | 514 (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 |
vLLM: supported · XLMRobertaModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · XLMRobertaModel · 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.
Weights-only memory for multilingual-e5-base: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.7 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.3 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.2 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 177quantized: 276adapter: 2merge: 4
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| djovak/embedic-base | finetune | — | 278M | S | mit | djovak | 2 | 2.3M |
| contextboxai/halong_embedding | finetune | — | 278M | S | apache-2.0 | contextboxai | 39 | 976.1k |
| upskyy/e5-base-korean | finetune | — | 278M | S | mit | upskyy | 3 | 164.8k |
| Xenova/multilingual-e5-base | quantized | — | — | — | — | Xenova | 3 | 163k |
| Metric-AI/armenian-text-embeddings-1 | finetune | — | 278M | S | — | Metric-AI | 21 | 89.2k |
| alunadiderot/setfit-e5-base-category-classifier_v2 | finetune | — | 278M | S | — | alunadiderot | 2 | 63.4k |
| BalyasnyAI/multilingual-e5-base | finetune | — | 278M | S | apache-2.0 | BalyasnyAI | 3 | 13.5k |
| lapa-llm/fineweb-mixtral-edu-score | finetune | — | 278M | S | mit | lapa-llm | 0 | 12.4k |
| lapa-llm/alignment-score-model | finetune | — | 278M | S | mit | lapa-llm | 0 | 12.3k |
| lapa-llm/fineweb-nemotron-edu-score | finetune | — | 278M | S | mit | lapa-llm | 0 | 12.2k |
| lapa-llm/manipulative-score-model | finetune | — | 278M | S | mit | lapa-llm | 2 | 12k |
| lapa-llm/gec-score-model | finetune | — | 278M | S | mit | lapa-llm | 0 | 12.1k |
| lapa-llm/fasttext-quality-score | finetune | — | 278M | S | mit | lapa-llm | 0 | 12.1k |
| KarBik/legal-french-matroshka | finetune | — | 278M | S | — | KarBik | 0 | 6.6k |
| dinab/multilingual-e5-base-Q4_K_M-GGUF | quantized | GGUF | — | — | mit | dinab | 0 | 6.3k |
| mjwong/multilingual-e5-base-xnli | finetune | — | 278M | S | mit | mjwong | 1 | 5.8k |
| antoinelouis/french-me5-base | quantized | — | 115M | S | mit | antoinelouis | 0 | 5.4k |
| groonga/multilingual-e5-base-Q4_K_M-GGUF | quantized | GGUF | — | — | mit | groonga | 0 | 4.7k |
| mjwong/multilingual-e5-base-xnli-anli | finetune | — | 278M | S | cc-by-nc-4.0 | mjwong | 0 | 4.3k |
| bqbbao6/vietnamese-legal-embedding | finetune | — | 278M | S | — | bqbbao6 | 0 | 4.1k |
| louisbrulenaudet/lemone-router-l | finetune | — | 560M | S | apache-2.0 | louisbrulenaudet | 0 | 3.3k |
| Metric-AI/armenian-text-embeddings-2-base | finetune | — | 278M | S | mit | Metric-AI | 4 | 2.9k |
| Pustekhan-ITB/indoedu-e5-base | quantized | GGUF | 278M | S | — | Pustekhan-ITB | 0 | 2.8k |
| Nurlykhan/kazembed-v5 | finetune | — | 278M | S | apache-2.0 | Nurlykhan | 2 | 2.4k |
| cstr/multilingual-e5-base-GGUF | quantized | GGUF | — | — | mit | cstr | 0 | 2.1k |
| bachngo/int-e5-base-5tv5 | finetune | — | 278M | S | — | bachngo | 0 | 1.9k |
| dinab/multilingual-e5-base-Q8_0-GGUF | quantized | Q8_0 | — | — | mit | dinab | 2 | 1.7k |
| novelcore/aristotle | finetune | — | 278M | S | apache-2.0 | novelcore | 0 | 1.6k |
| ipsnan/keywordsextraction | finetune | — | 278M | S | mit | ipsnan | 0 | 1.4k |
| antoinelouis/crossencoder-me5-base-mmarcoFR | finetune | — | 278M | S | mit | antoinelouis | 1 | 1.1k |
| bqbbao6/VN_legal_embedding_512 | finetune | — | 278M | S | — | bqbbao6 | 0 | 1.1k |
| Funghang/e5-nepali-qa-ir | finetune | — | 278M | S | cc-by-nc-4.0 | Funghang | 3 | 960 |
| Tamil-ai/tamil-embed-base | finetune | — | 278M | S | apache-2.0 | Tamil-ai | 0 | 1.1k |
| tatsuyaaaaaaa/multilingual-e5-base-gguf | quantized | gguf | — | — | mit | tatsuyaaaaaaa | 0 | 1k |
| onnx-community/multilingual-e5-base-ONNX | quantized | — | — | — | mit | onnx-community | 0 | 1k |
| thuan220401/halong_embedding | finetune | — | 278M | S | apache-2.0 | thuan220401 | 0 | 953 |
| oridror/e5-base-hebrew-qa-v2-myd-r1 | finetune | — | 278M | S | apache-2.0 | oridror | 0 | 789 |
| bqbbao6/vietnamese-legal-embedding-wsgm | finetune | — | 278M | S | — | bqbbao6 | 0 | 782 |
| novelcore/Orpheas | finetune | — | 278M | S | apache-2.0 | novelcore | 0 | 777 |
| isy-thl/multilingual-e5-base-learning-outcome-skill-tuned | finetune | — | 278M | S | — | isy-thl | 0 | 738 |
| Date | Commit | SHA |
|---|---|---|
| 2026-04-02 | Add evaluation results for model intfloat/multilingual-e5-base revision d13f1b27baf31030b7fd040960d60d909913633f (#31) | d128750 |
| 2025-02-17 | Add exported openvino model 'openvino_model.xml' (#24) | 8351938 |
| 2025-02-17 | Add exported onnx model 'model_O4.onnx' (#23) | f5bd48c |
| 2025-02-17 | Add exported onnx model 'model_qint8_avx512_vnni.onnx' (#22) | e0d62dd |
| 2024-02-15 | Update README.md | d13f1b2 |
| 2024-02-14 | Add link to new paper (#18) | 87d6695 |
| 2023-09-08 | Adding ONNX file of this model (#11) | 167cf6a |
| 2023-08-07 | Update README.md | b1a0e29 |
| 2023-07-27 | add sentence similarity tag | 061a1bb |
| 2023-07-20 | Update README.md | 1292863 |
| 2023-07-19 | track tokenizer.json with lfs | 1881441 |
| 2023-06-20 | Adding `safetensors` variant of this model (#6) | a1c23e4 |
| 2023-06-18 | Update README.md | 716cad0 |
| 2023-06-18 | sentence transformers (#5) | 830e3a9 |
| 2023-05-22 | Update README.md | f7d866c |
| 2023-05-19 | upload model weights | 8bbd5fa |
| 2023-05-19 | initial commit | ddf1713 |
Hosted endpoints observed for multilingual-e5-base, 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-base | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
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).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:34 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
