bge-base-en-v1.5

BAAI MIT out 3 years ago

109M parameters, text in, embeddings out, 512 tokens of context. 2 providers serve it from $0.005 per million input tokens.

Verified 2026-10-25 Rank #9 in Embeddings · score 107.6 method v1 Sources 3 Downloads 30d 8.6M · #13 of 619 tracked

Changed this week: 3 new quantized builds on the Hub (30 in all).2026-10-24

Can I run it?0.1GB at INT4Estimatefits a 16 GB cardmethod

What does it cost?$0.005/1M incheapest of 1DeepInfra2026-10-25

Can I use it?MITPermissivelicence file2026-10-24

Does it work?65.14on MTEB#14 of 64 measuredleaderboard2026-10-24

Do people use it?8.6Mdownloads, 30 days#13 of 619 we track · top 2%+6 likes, downloads −4% this week538 likesHugging Face2026-10-24

Worth reading

Picked by rule from 4 tracked pieces: the lab's own post, the most shared, a field report, the latest.

4 best of 4 tracked

The 1 pick above, plus these 3. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

Articlebge-base-en-v1.5 by BAAI | Mixpeek Model Hubmixpeek.com · undated
Articlebge-base-en-v1.5 — Use Cases, Pros & Cons | AI Tools Directoryaiappdex.com · undated
ArticleThe guide to bge-base-en-v1.5 | BAAIzilliz.com · 2024-08-17

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

#	Cheapest 2	In /1M	Out /1M	Context	Quant	Seen
1	DeepInfra	$0.005	—	512	—	Oct 25
2	HF Inference	—	—	—	—	Oct 25

All 2 providers →

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 2 API providers; 30 quantized builds for local use; a big base for builders (502 fine-tunes, adapters and merges).

As a service2DeepInfra, HF Inference
On own hardware30quantized builds
Built on502501 fine-tunes · 1 adapters · 0 merges
In apps100+Hugging Face Spaces

Top Spaces running it: hysts/daily-papers ♥ 297 · HuggingFaceFW/finephrase ♥ 285 · cin-model/kotaemon-demo ♥ 206 · embedl/hfviewer ♥ 181

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.

#14 of 64 on MTEB so far

65.14. 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

The story so far

Weights, every dated article, and repo commits on one rail.

1 dated article and 13 repo commits so far

Teal is the weights (2023-09-11), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.

What people built on it

532 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

532 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.

GGUF ChristianAzinn/bge-base-en-v1.5-gguf for llama.cpp, Ollama, LM Studio 6.2k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

3 rows

Benchmarks 3 rows

measured third-party leaderboard row (3)author-reported number from the model card or eval filesNo 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	54.75 nDCG@10 x100 (mean of 10 tasks)	10 tasks, split=test	leaderboard	2026-10-24
measured MTEB · Embed text for search	65.14 mean(task) x100 over 41 tasks	41 tasks, split=test	leaderboard	2026-10-24
measured MTEB Reranking · Rerank search results	46.66 MAP x100 (mean of 2 tasks)	2 tasks, split=test	leaderboard	2026-10-24

Use-case evidence

2 use cases

What it is good at 2 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.

Facts

21 fields

Listed in Embeddings

Facts

bge-base-en-v1.5 has 109M 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 2023-09-11, last modified 2024-02-21. (HF API, observed 2026-10-24)

Pipeline tag	feature-extraction
Library	sentence-transformers
Architectures	BertModel
Model type	bert
Dtype	float32
Params by dtype	F32: 109,482,240 · I64: 512
Size band	S
MoE	no
Context length	512 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2401.03462, arXiv:2312.15503, arXiv:2311.13534, arXiv:2310.07554, arXiv:2309.07597
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 bge-base-en-v1.5: 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

Original model Family: BAAI/bge-v1.5 532 derivatives on the Hub

quantized: 30finetune: 501adapter: 1

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Xenova/bge-base-en-v1.5	quantized	—	—	—	mit	Xenova	27	35.2M
datasocietyco/bge-base-en-v1.5-course-recommender-v5	finetune	—	109M	S	—	datasocietyco	23	18M
abhinand/MedEmbed-base-v0.1	finetune	—	109M	S	apache-2.0	abhinand	22	2.4M
Qdrant/bge-base-en-v1.5-onnx-Q	quantized	—	—	—	mit	Qdrant	1	1.9M
minishlab/M2V_base_output	quantized	—	7.56M	S	mit	minishlab	10	826.6k
tstadel/answer-classification-setfit-v2-binary	finetune	—	109M	S	—	tstadel	0	154.2k
philschmid/bge-base-financial-matryoshka	finetune	—	109M	S	apache-2.0	philschmid	10	70.7k
RishuD7/bge-base-en-v1.5-82-keys-phase-7-exp_v1	finetune	—	109M	S	apache-2.0	RishuD7	0	53.1k
Shashwat13333/bge-base-en-v1.5_v4	finetune	—	109M	S	apache-2.0	Shashwat13333	0	30.3k
knowledgator/modern-gliner-bi-large-v1.0	finetune	—	—	—	apache-2.0	knowledgator	65	18.5k
OpenVINO/bge-base-en-v1.5-fp16-ov	finetune	-fp16	—	—	mit	OpenVINO	0	16.3k
zks2856/PairQual-Scorer-en	finetune	—	110M	S	mit	zks2856	0	8.7k
axondendriteplus/Legal-Embed-bge-base-en-v1.5	finetune	—	109M	S	apache-2.0	axondendriteplus	3	7.6k
OpenVINO/bge-base-en-v1.5-int8-ov	finetune	int8	—	—	mit	OpenVINO	1	6.3k
ChristianAzinn/bge-base-en-v1.5-gguf	quantized	gguf	—	—	mit	ChristianAzinn	0	6.2k
minishlab/M2V_base_glove	finetune	—	102M	S	mit	minishlab	4	5.6k
Ihor/gliner-biomed-bi-large-v1.0	finetune	—	—	—	apache-2.0	Ihor	1	4.8k
JJTsao/fine-tuned_movie_retriever-bge-base-en-v1.5	finetune	—	109M	S	apache-2.0	JJTsao	1	4.1k
minishlab/M2V_base_glove_subword	quantized	—	103M	S	mit	minishlab	2	4.1k
knowledgator/gliner-bi-base-v2.0	finetune	—	—	—	apache-2.0	knowledgator	7	3k
bnkc123/bge-base-financial-matryoshka	finetune	—	109M	S	apache-2.0	bnkc123	0	2.3k
iris49/3gpp-embedding-model-v0	finetune	—	109M	S	apache-2.0	iris49	4	2.1k
knowledgator/gliner-bi-large-v2.0	finetune	—	—	—	apache-2.0	knowledgator	18	1.3k
knowledgator/gliner-bi-small-v2.0	finetune	—	—	—	apache-2.0	knowledgator	5	1.7k
knowledgator/gliner-bi-edge-v2.0	finetune	—	—	—	apache-2.0	knowledgator	8	1.4k
bhlim/bge-base-patentmatch	finetune	—	109M	S	apache-2.0	bhlim	4	1.2k
NaqibL/bge-base-sgmarket-v2	finetune	—	109M	S	—	NaqibL	0	1.3k
deven96/bge-base-en-v1.5	quantized	—	—	—	mit	deven96	0	1.2k
potsu-potsu/bge-base-biomedical-matryoshka-v3	finetune	—	109M	S	apache-2.0	potsu-potsu	0	1.1k
gridwayai/bge-nuclear-finetuned-5	finetune	—	109M	S	—	gridwayai	0	962
cstr/bge-base-en-v1.5-GGUF	quantized	GGUF	—	—	mit	cstr	0	940
BarraHome/vmware-embeddings-large-v1	finetune	—	109M	S	mit	BarraHome	0	890
Nishanth7803/bge-base-finetuned-financial	finetune	—	109M	S	apache-2.0	Nishanth7803	2	751
plaguss/bge-base-argilla-sdk-matryoshka	finetune	—	109M	S	apache-2.0	plaguss	5	541
moritzglnr/bge-base-financial-matryoshka	finetune	—	109M	S	apache-2.0	moritzglnr	2	675
akashmaggon/bge-base-financial-matryoshka	finetune	—	109M	S	apache-2.0	akashmaggon	0	734
marksverdhei/wordnet-sense-bge-small	finetune	—	109M	S	—	marksverdhei	0	713
NickyNicky/bge-base-financial-matryoshka_test_0	finetune	—	109M	S	apache-2.0	NickyNicky	1	581
deba2012ddx/minja_bge_ft	finetune	—	109M	S	—	deba2012ddx	0	613
Muhammad2003/router-embedding	finetune	—	109M	S	—	Muhammad2003	2	499

Repository changelog

13 commits

changed in the last 7 daysOther: 2026-10-24all changes

Repository changelog 13 commits

Date	Commit	SHA
2024-02-21	Onnx Support (#6)	a5beb1e
2024-02-02	Update README.md	2d66e08
2023-12-18	Adding `safetensors` variant of this model (#1)	70e8c52
2023-10-12	update	617ca48
2023-09-27	Update modules.json	1dafa38
2023-09-15	update	38713fb
2023-09-14	Update README.md	0a2d014
2023-09-12	update	96c0f5b
2023-09-12	update	7dd8f5d
2023-09-12	update	7d8fee1
2023-09-12	update	08e3d2c
2023-09-11	upload	6221169
2023-09-11	initial commit	d803ca7

All providers

2 providers · 2 endpoints

Where to run 2 providers · 2 endpoints

Hosted endpoints observed for bge-base-en-v1.5, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.0050/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
DeepInfra hf, deepinfra	BAAI/bge-base-en-v1.5	512	—	$0.0050	—	—	—	—	live	2026-10-25
HF Inference hf	BAAI/bge-base-en-v1.5	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

4 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.

Analysis3

bge-base-en-v1.5 by BAAI | Mixpeek Model Hub

mixpeek.com616 words

The model produces 768-dimensional vectors over a 512-token window with 109.5 million parameters. It averages 63.55 on the MTEB English table, which includes 56 English datasets.generated, cited

BGE Base EN V1.5 API Pricing & Benchmarks | LMSpeed

lmspeed.net234 words

BGE Base EN V1.5 converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. Third-party providers like DeadlySignal charge $2.00/M for input and output, while DeepInfra lists input at $0.0050/M with a context limit of 512 tokens. Official API pricing remains not published.written, reviewed, cited

The guide to bge-base-en-v1.5 | BAAI

zilliz.com2024-08-17561 words

BAAI released bge-base-en-v1.5, a general embedding model for English text that transforms input into compact vectors. The model features 768 dimensions, a 512 token limit, and achieves a 63.55 MTEB avg score. Developers can generate embeddings using PyMilvus or the official FlagEmbedding SDK before storing them in Zilliz Cloud.written, reviewed, cited

Community1

bge-base-en-v1.5 — Use Cases, Pros & Cons | AI Tools Directory

aiappdex.com

Papers

5 papers

Papers 5

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).

Long Context Compression with Activation Beacon cited in card

Peitian Zhang, Zheng Liu, Shitao Xiao +3 · 2024-01-07 · PDF · HF paper page (30 upvotes)
A Multi-Task Embedder For Retrieval Augmented LLMs cited in card

Peitian Zhang, Shitao Xiao, Zheng Liu +2 · 2023-10-11 · PDF · HF paper page (6 upvotes)
LM-Cocktail: Resilient Tuning of Language Models via Model Merging cited in card

Shitao Xiao, Zheng Liu, Peitian Zhang +1 · 2023-11-22 · PDF · HF paper page (3 upvotes)
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval cited in card

Zheng Liu, Chaofan Li, Shitao Xiao +2 · 2023-12-24 · PDF · HF paper page (2 upvotes)
C-Pack: Packed Resources For General Chinese Embeddings cited in card

Shitao Xiao, Zheng Liu, Peitian Zhang +3 · 2023-09-14 · PDF · HF paper page (2 upvotes)

Similar models

3 models

Similar models

bge-base-en · 109M
same size band (S), same task (feature-extraction), fewer providers, permissive license
canine-c · 132M
same size band (S), same task (feature-extraction), fewer providers, permissive license
bart-base · 139M
same size band (S), same task (feature-extraction), fewer providers, permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:32 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 bge-base-en-v1.5

Watch this model

/feeds/models/BAAI--bge-base-en-v1.5.xml(RSS 2.0) · every change to bge-base-en-v1.5
/feeds/families/BAAI--bge-v1.5.xml(RSS 2.0) · every change across the bge-v1.5 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.