Embedding models 24
We track 24 open embedding models from 8 labs, 8 of them released in the 12 months to 7 Nov 2026. The newest is embeddinggemma-2 (14 Sep 2026) and the most downloaded is Qwen3-Embedding-0.6B, with 8,620,434 downloads in 30 days. 19 fit a 16 GB GPU at 4-bit, and none has a hosted API in our data.
Embedding models turn inputs into vectors that can be compared for search, retrieval and clustering. Sentence Transformers supports building and serving these models; MTEB evaluates their behaviour across tasks. A good retrieval result depends on the corpus and query distribution as well as the model.
What the category covers
The core job is turning text into a fixed-length vector for similarity comparison. Around that sit several related jobs that use the same machinery.
Rerankers are one example. A retrieval system typically fetches many candidates by vector similarity, then reranks the shortlist with a model that looks at the query and document together, which adds query-time computation and can improve relevance. Repository names carrying rerank are doing that job, not the first-stage one. Classification models, reward models and token-level variants also sit in this family, as related non-generative tasks, although their architectures and outputs differ.
Some models in our embedding category are encoders for other modalities, including audio and code. The naming is the quickest signal.
How they are measured
MTEB is the shared benchmark, and its own description has widened: a multimodal toolbox for evaluating embeddings and retrieval systems, installed with pip install mteb, with a leaderboard hosted on Hugging Face.
MTEB spans task types rather than one, so a model can be strong at retrieval and weaker at clustering or classification. The leaderboard lets you filter to the tasks and languages you care about, and a model at the top of the overall table may be beaten on your language or your domain by something smaller.
A public leaderboard is a starting point for evaluation. Test representative queries against your own documents, including difficult negatives and the languages your users write. An aggregate benchmark result need not predict the ordering on that workload.
What serves them
Sentence Transformers provides tools to compute embeddings and train embedding and reranker models. Its README documents installation with pip install -U sentence-transformers, supported Python and PyTorch versions, and optional ONNX and OpenVINO backends. The model card determines the correct input formatting and whether a query needs a special prompt.
vLLM can serve these models too, in what it calls pooling mode. Its pooling documentation says pooling models are supported primarily for convenience and that this is not guaranteed to provide performance improvements over using Hugging Face Transformers or Sentence Transformers directly, with optimisation listed as planned work. Because some architectures support both generative and pooling tasks, the supported-models doc says to specify --runner pooling explicitly so the model is used in pooling mode instead of generative mode. Separate pages cover classification, embedding, reward, scoring and token-level usage.
For embeddings at scale, the vector store matters as much as the model, and that is a choice outside the model itself.
The hardware reality
Hardware still matters for embedding workloads. Model size, input length and batch size affect memory and throughput. A CPU deployment may suit occasional queries while large indexing jobs benefit from batching on an accelerator. Measure the actual documents and queries before sizing a service.
The costs that matter are elsewhere. Embedding dimension drives storage and search cost across the whole corpus, so a larger vector multiplies your index, and some model families support truncating dimensions to trade accuracy for size. Maximum sequence length determines how you chunk documents. Reranking is the expensive step at query time, because it runs the model once per candidate pair rather than once per document.
The operational constraint people hit is not speed but consistency: changing embedding model means re-embedding the entire corpus, since vectors from different models are not comparable.
Licence patterns
Embedding checkpoints can carry permissive or custom terms. Our Apache 2.0, MIT and comparison pages explain common permissive licences.
A library’s licence is separate from the licences of the checkpoints it loads. Some model families have their own conditions, such as those described on our Gemma terms page. Check the actual checkpoint’s licence and any incorporated base model before commercial use.
This summarises licence text. It is not legal advice.
FAQ
Is a higher MTEB score always better for my use case?
No. MTEB spans multiple task types and languages, and the overall ranking can hide weakness on the task you need. Filter the leaderboard, then test on your own data.
Should I serve embeddings with vLLM?
Only if it simplifies your stack. vLLM’s own documentation says pooling support exists primarily for convenience and is not guaranteed to beat Sentence Transformers or Transformers directly.
What is the difference between an embedding model and a reranker?
An embedding model encodes each text independently so vectors can be compared cheaply at scale. A reranker scores a query and a candidate together, which adds computation per candidate and can improve relevance, so it typically runs on a shortlist.
Can I switch embedding models later?
Usually this requires rebuilding the index with the new model. Independently trained encoders do not generally produce compatible vector spaces; retain the old encoder until migration is complete.
Pick a view
All modelsNewest
| Model | Released | Type | Size | Memory at 4-bit | 16 GB GPU | Downloads, 30 days | Cheapest API, blended / 1M |
|---|---|---|---|---|---|---|---|
| 14 Sep 2026 | Embedding | 744M | 0.6 GB | Fits | 517,987 | No tracked API | |
| 25 Aug 2026 | Embedding | 2.7B | 1.9 GB | Fits | 12,392 | No tracked API | |
| 14 Jul 2026 | Embedding | 8B | 6.5 GB | Fits | 128,586 | No tracked API | |
| 14 Jul 2026 | Embedding | 1.1B | 1.3 GB | Fits | 324,819 | No tracked API | |
| 20 Apr 2026 | Embedding | 312M | 0.8 GB | Fits | 83,891 | No tracked API | |
| 20 Apr 2026 | Embedding | 97M | 0.2 GB | Fits | 188,743 | No tracked API | |
| 30 Mar 2026 | Embedding | 596M | 1.4 GB | Fits | 217,416 | No tracked API | |
| 10 Mar 2026 | Embedding | 2.3B | 2.2 GB | Fits | 133,622 | No tracked API | |
| 4 Nov 2025 | Embedding | 11.8B | 8.4 GB | Fits | 11,560 | No tracked API | |
| 16 Oct 2025 | Embedding | 1.2B | 1.1 GB | Fits | 297,423 | No tracked API | |
| 16 Oct 2025 | Embedding | 1.2B | 1.1 GB | Fits | 350,783 | No tracked API | |
| 29 Sep 2025 | Embedding | 474M | 1.3 GB | Fits | 62 | No tracked API |
Most downloaded
| Model | Released | Type | Size | Memory at 4-bit | 16 GB GPU | Downloads, 30 days | Cheapest API, blended / 1M |
|---|---|---|---|---|---|---|---|
| 3 Jun 2025 | Embedding | 596M | 1.4 GB | Fits | 8,620,434 | No tracked API | |
| 17 Jul 2025 | Embedding | 48M | 0.2 GB | Fits | 6,828,205 | No tracked API | |
| 2 Mar 2022 | Embedding | Unknown | Unknown | Unknown | 1,359,122 | No tracked API | |
| 17 Jul 2025 | Embedding | 303M | 0.2 GB | Fits | 1,085,038 | No tracked API | |
| 16 Feb 2023 | Embedding | Unknown | Unknown | Unknown | 679,663 | No tracked API | |
| 14 Sep 2026 | Embedding | 744M | 0.6 GB | Fits | 517,987 | No tracked API | |
| 2 Mar 2022 | Embedding | Unknown | Unknown | Unknown | 501,075 | No tracked API | |
| 16 Oct 2025 | Embedding | 1.2B | 1.1 GB | Fits | 350,783 | No tracked API | |
| 14 Jul 2026 | Embedding | 1.1B | 1.3 GB | Fits | 324,819 | No tracked API | |
| 16 Oct 2025 | Embedding | 1.2B | 1.1 GB | Fits | 297,423 | No tracked API | |
| 30 Apr 2024 | Embedding | Unknown | Unknown | Unknown | 231,063 | No tracked API | |
| 30 Mar 2026 | Embedding | 596M | 1.4 GB | Fits | 217,416 | No tracked API |
Smallest that fit 16 GB
| Model | Released | Type | Size | Memory at 4-bit | 16 GB GPU | Downloads, 30 days | Cheapest API, blended / 1M |
|---|---|---|---|---|---|---|---|
| 17 Jul 2025 | Embedding | 48M | 0.2 GB | Fits | 6,828,205 | No tracked API | |
| 20 Apr 2026 | Embedding | 97M | 0.2 GB | Fits | 188,743 | No tracked API | |
| 2 Mar 2022 | Embedding | 125M | 0.4 GB | Fits | 697 | No tracked API | |
| 2 Mar 2022 | Embedding | 125M | 0.4 GB | Fits | 9,005 | No tracked API | |
| 4 Dec 2024 | Embedding | 125M | 0.4 GB | Fits | 208,133 | No tracked API | |
| 4 Dec 2024 | Embedding | 278M | 0.5 GB | Fits | 72,421 | No tracked API | |
| 17 Jul 2025 | Embedding | 303M | 0.2 GB | Fits | 1,085,038 | No tracked API | |
| 20 Apr 2026 | Embedding | 312M | 0.8 GB | Fits | 83,891 | No tracked API | |
| 29 Sep 2025 | Embedding | 474M | 1.3 GB | Fits | 62 | No tracked API | |
| 3 Jun 2025 | Embedding | 596M | 1.4 GB | Fits | 8,620,434 | No tracked API | |
| 30 Mar 2026 | Embedding | 596M | 1.4 GB | Fits | 217,416 | No tracked API | |
| 14 Sep 2026 | Embedding | 744M | 0.6 GB | Fits | 517,987 | No tracked API |
Releases per month
8 in 12 months| Month | Total |
|---|---|
| Dec 2025 | 0 |
| Jan 2026 | 0 |
| Feb 2026 | 0 |
| Mar 2026 | 2 |
| Apr 2026 | 2 |
| May 2026 | 0 |
| Jun 2026 | 0 |
| Jul 2026 | 2 |
| Aug 2026 | 1 |
| Sep 2026 | 1 |
| Oct 2026 | 0 |
| Nov 2026 | 0 |
Cheapest hosted APIs
All API pricesWe have not recorded API pricing for these embedding models yet.