The story so far
Weights, every dated article, and repo commits on one rail.
21 repo commits since the weights landed
Teal is the weights (2022-03-02), grey ticks are repo commits.
distiluse-base-multilingual-cased-v2
sentence-transformers Apache 2.0 out 5 years ago
135M parameters, text in, embeddings out, 512 tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #31 in Embeddings · score 93.9 method v1 Sources 3 Downloads 30d 870.4k · #124 of 619 tracked
Can I run it?0.1GB at INT4Estimatefits a 16 GB cardmethodCommunity: distiluse-base-multilingual-cased-v2 - 135M | GPU Requirements | vram.run →
Do people use it?870.4kdownloads, 30 days#124 of 619 we track · top 20%+3 likes, downloads −1% this week219 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; 1 quantized build for local use.
- As a service1HF Inference
- On own hardware1quantized builds
- Built on1313 fine-tunes · 0 adapters · 0 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: JohnSmith9982/ChuanhuChatGPT ♥ 921 · MILVLG/IMPChat ♥ 12 · shibing624/ChatPDF ♥ 5 · JohnSmith9982/ChuanhuChatGPT_Beta ♥ 4
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, 0.2 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
What people built on it
14 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
14 derivatives on the Hub, most of them fine-tunes
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.
What the card says
1 cited sentence
Summary generated, cited
It maps sentences and paragraphs to a 512 dimensional dense vector space for applications like clustering or semantic search.[1]
Generated 2026-10-07 15:02 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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 searchstructuraldecision-model estimate p=1.00tag: sentence-transformerspipeline: sentence-similarity+1 more
- Work across languagesstructuraldecision-model estimate p=1.00name: multilingualtag: multilingual+1 more
- Run on a laptop or phonestructuraldecision-model estimate p=0.99fits: edge
Facts
21 fields
Listed in Embeddings
Facts
- distiluse-base-multilingual-cased-v2 has 135M parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 512 tokens (512). (config.json max_position_embeddings, observed 2026-10-24)
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2022-03-02, last modified 2025-03-06. (HF API, observed 2026-10-24)
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | DistilBertModel |
| Model type | distilbert |
| Params by dtype | F32: 134,734,080 |
| Size band | S |
| MoE | no |
| Context length | 512 (config.json max_position_embeddings) |
| Languages | multilingual, ar, bg, ca, cs, da, de, el, en, es, et, fa, fi, fr, gl, gu, he, hi, hr, hu, hy, id, it, ja, ka, ko, ku, lt, lv, mk, mn, mr, ms, my, nb, nl, pl, pt, ro, ru, sk, sl, sq, sr, sv, th, tr, uk, ur, vi |
| Papers | arXiv:1908.10084 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 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 distiluse-base-multilingual-cased-v2: 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) | 0.2 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
14 variants
Lineage
quantized: 1finetune: 13
Top variants (14 shown, ranked by downloads)
Repository changelog
21 commits
Repository changelog 21 commits
| Date | Commit | SHA |
|---|---|---|
| 2025-03-06 | Remove deprecated (SEB) evaluation results section | bfe45d0 |
| 2024-11-05 | Add exported openvino model 'openvino_model_qint8_quantized.xml' | dad0fa1 |
| 2024-10-11 | Add new SentenceTransformer model with an openvino backend | b7d1937 |
| 2024-10-11 | Add new SentenceTransformer model with an openvino backend | 2bbab3f |
| 2024-10-11 | Add exported ONNX model 'model_qint8_avx512_vnni.onnx' | acc8502 |
| 2024-10-11 | Add exported ONNX model 'model_qint8_avx512.onnx' | 8eccd57 |
| 2024-10-11 | Add exported ONNX model 'model_quint8_avx2.onnx' | 76a1ba5 |
| 2024-10-11 | Add exported ONNX model 'model_qint8_arm64.onnx' | 95d20b1 |
| 2024-10-11 | Add exported ONNX model 'model_O4.onnx' | efa279e |
| 2024-10-11 | Add exported ONNX model 'model_O3.onnx' | 8ce6ee5 |
| 2024-10-11 | Add exported ONNX model 'model_O2.onnx' | 808c162 |
| 2024-10-11 | Add exported ONNX model 'model_O1.onnx' | b4a8309 |
| 2024-10-11 | Add new SentenceTransformer model with an onnx backend | 471e36f |
| 2024-03-27 | Adding `safetensors` variant of this model (#10) | 03a0532 |
| 2024-02-12 | Update Sentence Transformers metadata (#8) | 501a2af |
| 2023-11-02 | Update README.md (#2) | 8f30462 |
| 2022-06-15 | Add TF weights | 896fbac |
| 2021-11-02 | Update README.md | 486c69f |
| 2021-08-05 | Update README.md | b0eb08f |
| 2021-06-22 | Add new SentenceTransformer model. | fcd5c2b |
| 2021-06-22 | initial commit | 71b2a81 |
All providers
1 provider · 1 endpoint
Where to run 1 providers · 1 endpoints
Hosted endpoints observed for distiluse-base-multilingual-cased-v2, 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 | sentence-transformers/distiluse-base-multilingual-cased-v2 | — | — | — | — | — | — | — | live | 2026-10-25 |
Articles and coverage
3 pieces
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.
Analysis2
savrn.com1,782 words
distiluse-base-multilingual-cased-v2 is a 135M parameter open-weight model for sentence similarity released under Apache License 2.0 with a 512-token context and 119,547 vocabulary size. It requires about 0.3 GB of GPU memory at 16-bit precision but drops to 0.1 GB at 4-bit, fitting on a single MI300X GPU for $1.85 an hour. First published on 2022-03-02, the model draws 1M downloads a month and outputs 512-dimensional vectors for tasks like clustering or semantic search.written, reviewed, cited
- The model repository totals 5.3 gigabytes across 30 files, requiring selective downloads to match runtime needs.
- Apache License 2.0 requires keeping the license and copyright notices and any NOTICE file when redistributing.
- Long documents must be chunked before embedding because the 512-token context limit prevents processing full texts at once.
vram.run203 words
distiluse-base-multilingual-cased-v2 is a 135M parameter model designed for sentence-similarity tasks with 1.0M downloads. At Q4 quantization it requires 0GB of VRAM and runs comfortably on the GeForce RTX 4090 at 9745 tok/s. The model also performs on the M4 Max 128GB at 3566 tok/s.written, reviewed, cited
Community1
github.comauthorityabout the distiluse family676 words
The distiluse-base-multilingual-cased model adds a dense layer on top of mean pooling to transform DistilBERT's 768-dimensional output into 512 dimensions, matching the Universal Sentence Encoder's format. This architecture allows the model to function as a student in a knowledge distillation setup where the teacher is the multilingual Universal Sentence Encoder. The method enables extending sentence embedding models to new languages using parallel training data.written, reviewed, cited
- The distiluse-base-multilingual-cased model uses the training process from the paper Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation.
Papers
1 paper
Papers 1
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
- nomic-embed-text-v1.5 · 137M same size band (S), same task (sentence-similarity), permissive license
- nomic-embed-text-v1 · 137M same size band (S), same task (sentence-similarity), permissive license
- clip-ViT-B-32-multilingual-v1 · 135M 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 21:35 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:02 UTC · Last verified 2026-10-25
Follow distiluse-base-multilingual-cased-v2
Watch this model
- /feeds/models/sentence-transformers--distiluse-base-multilingual-cased-v2.xml(RSS 2.0) · every change to distiluse-base-multilingual-cased-v2
- /feeds/families/sentence-transformers--distiluse.xml(RSS 2.0) · every change across the distiluse family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.