Skip to content
Local AI Wizard
Your machine
Theme

BGE-M3

BAAI · BAAI/bge-m3

Weights license: MIT · code and components may use other terms

MTEB (Multilingual, v2)59.6 / 100mean(task) · independent run
Memory needed~3 GB8-bit planning estimate · not measured
Parameters0.57 BSee technical details for the basis
Dimensions · context1,0248,192 tokens

Quality

Reported by the publisher

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Quality × memory

No comparable quality × memory pair

Embedding memory estimates cluster at a few GB, so a quality × memory chart would not separate these models; MTEB is ranked above instead.

Consider it for

Consider BGE-M3 for retrieval and semantic search: it turns text into 1,024-dimension vectors.

Check first

The publisher states no memory figure; the hardware list uses a ~3 GB planning estimate, a ceiling and not a measurement. See the prompt format under How to run. PT-BR is confirmed by a source.

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by the embedding planning estimate (8-bit weights, 20% allowance, 2 GB reserve). Not a measured fit.

Measured speed

No published measurement for this checkpoint

Throughput (texts per second) is shown only when a source publishes it with hardware, build and setup. It is never estimated.

How to run

The planning estimate uses 8-bit weights, 20% working allowance and a 2 GB reserve; it is a ceiling, not a measurement.

Runs in
Ollama, Sentence Transformerssource
Query/document prompts
No instruction needed on queries (model card).
Languages · PT-BR
100+ working languages (model card)PT-BR confirmed by a source

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · FlagEmbedding
pip install -U FlagEmbedding
FlagEmbedding · model card · Generate Embedding for text
from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',  
                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation

sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

embeddings_1 = model.encode(sentences_1, 
                            batch_size=12, 
                            max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
                            )['dense_vecs']
embeddings_2 = model.encode(sentences_2)['dense_vecs']
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# [[0.6265, 0.3477], [0.3499, 0.678 ]]
Setup stated first by the source · FlagEmbedding
pip install -U FlagEmbedding
FlagEmbedding · model card · Generate Embedding for text
from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation

sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)

# you can see the weight for each token:
print(model.convert_id_to_token(output_1['lexical_weights']))
# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, 
#  {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]


# compute the scores via lexical mathcing
lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
print(lexical_scores)
# 0.19554901123046875

print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
# 0.0

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
BAAI/bge-m3
Task
embeddings for search (feature extraction)
Library in source
Ollama, Sentence Transformers
Weight license
MIT
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Parameter basis
568M from the MTEB model metadata and Snowflake's comparison table; Ollama lists 567M. The Hub shows no safetensors count (weights are a PyTorch .bin file).
Announced
2024-01-30

Dense, sparse and multi-vector (ColBERT) outputs in one model. The card states 8,192 tokens and no Matryoshka support.

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-07. Each value cites its source (the publisher's card or the MTEB results dataset); estimates are labelled as estimates, and a value no source states stays empty. A repository commit is not a model release date.