Skip to content

Sentence Transformers · Embedding

All MiniLM L6 V2

Sentence TransformersEmbeddingsentence familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (5 May 2026).

An embedding model with 128 token limit. It has 23 million parameters and an embedding dimension of 384.

llminfo IQ
76.0
Market median price
$0.005 /1M
Max context
512
Listings
6

Evidence and sources

🤗 sentence-transformers/all-MiniLM-L6-v223M paramsllminfo IQ 76.0, ranked among embedding models. From 161 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 18 Apr 2021
All rankings: #31 in Bluesky discussions this week #32 in Wikipedia pageviews this week #388 on OpenRouter today #396 on OpenRouter this month #403 on OpenRouter this weekAll rankings: #31 in Bluesky discussions this week #32 in Wikipedia pageviews this week #388 on OpenRouter today #396 on OpenRouter this month #403 on OpenRouter this weekSources: DeepInfra data, IBM watsonx.ai Foundation Models data docs, Models.dev data, llminfo researchPrimary data from DeepInfra from IBM watsonx.ai Foundation Models: parameter count, deprecation date, description from Models.dev: weights availability from llminfo research: release date
Tags from its sources:open-sourceembeddingretrieval

Advantages and trade-offs

Compared with 10 embedding models, picked mainly by popularity and IQ

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (5 May 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 4 maker's prices; 7 market median prices.

Input & output

as stated by the model's providers
Text
Text
Embeddings

Listings

 Eurouterall-minilm-l6-v2Sources: EURouter data, IBM watsonx.ai Foundation Models data docs256
 Flowdotsentence-transformers/all-MiniLM-L6-v2Sources: FlowDot data, IBM watsonx.ai Foundation Models data docs512$0.005—
 Nous Portalsentence-transformers/all-minilm-l6-v2Sources: IBM watsonx.ai Foundation Models data docs, Nous Portal Inference Gateway data512$0.005—
 Digitaloceanall-mini-lm-l6-v2Sources: IBM watsonx.ai Foundation Models data docs, Models.dev data256$0.009—

2 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Embedding

MTEB(deu, v1)125 related benchmarks · 125 results
Show 119 more resultsHide 119 results
PairClassification
Source: MTEB Leaderboard data
Retrieval
Source: MTEB Leaderboard data
STS
Source: MTEB Leaderboard data

Rerank

Also known as: all-mini-lm-l6-v2, sentence-transformers/all-minilm-l6-v2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works