homeservicesworkaboutblogfree templatescontactFree Tools →Free AI ModelsResearch LibraryROI CalculatorSavings CalculatorAI Readiness ScoreHire vs. AutomateAutomation Quote
book a 30-min call
home / free-models / bge-m3

BGE-M3 (embeddings)

BAAI · China · MIT

Commercial use: Yes — free for commercial use

MIT. The reranker sibling (bge-reranker-v2-m3) is Apache 2.0. Both unrestricted.

What this means for your business

The model that does the searching in an AI-search or document-question system. Not the one that writes the answer — the one that finds the right pages first.

Why it should matter to you

Most "our AI does not know our business" problems are retrieval problems, and retrieval quality is set here rather than by which chatbot you bought. It is also the cheapest part of the stack to self-host, which means your documents can stay inside your network even if the answering model does not.

How it connects to our work

Every retrieval system we build runs an embedding model plus a reranker, and the reranker is the step teams most often skip. It costs very little and it is usually the difference between a search that feels useful and one that does not.

From our field notesThe subscription bought a reader, not a library. This is the part that builds the library.

Parameters568M
Active per token568M
Context8K
Modalityembeddings
Memory @ Q4_K_M~0.5 GB
Memory @ Q8_0~0.8 GB
LicenceMIT
Last verified2026-09

Advantages

  • The default open embedding model for retrieval — 38M downloads and rising
  • Handles 100+ languages, dense and sparse retrieval in one model
  • Tiny and cheap to self-host, so your documents never leave your network to be embedded
  • Pairs with bge-reranker-v2-m3, which reliably improves retrieval quality for very little compute

Disadvantages

  • 8K context per chunk, so long documents must be split sensibly
  • Generic embeddings place domain jargon poorly — your industry's vocabulary is not where the model expects
  • Being a Chinese-origin model, it draws the same procurement questions as the LLMs, despite never seeing a prompt

Reach for it when

The retrieval half of any RAG system. This is the component doing the actual searching, and it is almost always the one worth self-hosting first.

Where it falls down

Domain-specific matching out of the box. If your sector reuses common words with uncommon meanings, expect to add a reranker and a domain vocabulary rather than swapping in a bigger embedding model.

Running it

CPU is fine. Any GPU is instant. See the hardware sizing tables for how that maps to specific chips and cards, and the quantisation guide for what you give up at each bit width.

will it fitBGE-M3 (embeddings) against common GPUs
BGE-M3 (embeddings) at Q4_K_M
0 GB
BGE-M3 (embeddings) at Q8_0
0 GB
RTX 3060 12GB
0 GB
RTX 4060 Ti 16GB
0 GB
RTX 4090
0 GB
RTX 5090
0 GB
RTX 6000 Ada
0 GB
A100 80GB
0 GB
H100 80GB
0 GB
Weight sizes for BGE-M3 (embeddings) as recorded in this directory; GPU memory from the hardware table on the directory hub. Weights only: context adds KV cache.
where the weights fitGPU and Mac memory, checked
Q4_K_MQ8_0
RTX 3060 12GB (12 GB)
RTX 4060 Ti 16GB (16 GB)
RTX 4090 (24 GB)
RTX 5090 (32 GB)
RTX 6000 Ada (48 GB)
A100 80GB (80 GB)
H100 80GB (80 GB)
Mac, 16 GB unified
Mac, 24 GB unified
Mac, 32 GB unified
Mac, 36 GB unified
Mac, 64 GB unified
Mac, 96 GB unified
Mac, 128 GB unified
Mac, 192 GB unified
Mac, 512 GB unified
✓ fits with room for context, ~ fits with under 15% headroom, ✕ does not fit. Weights only, computed from the figures on this page.

Free tiers carrying this model

ProviderTypeThe catchLive limits
Hugging Face Inference ProvidersAggregatorThe free credit is genuinely small — this is for trying a model, not running one. The Hub's real value here is free unlimited weight downloads.check →

Jurisdiction: China

This is the crucial split most write-ups miss: using a Chinese lab's HOSTED API sends your data to Chinese infrastructure and is a real procurement question. Downloading their OPEN WEIGHTS and running them on your own hardware, or on a Western host, sends nothing anywhere. DeepSeek and Z.ai publish under MIT; Alibaba publishes most of Qwen3 under Apache 2.0. Those are among the most permissive licences on this page.

Watch for: Several US states and a number of government bodies restrict Chinese-hosted AI services on official devices. That restriction is about the hosted service, not about the weights running in your own VPC — but expect to have to explain the difference to a security reviewer.

Frequently asked

Can I use BGE-M3 (embeddings) commercially?

MIT. The reranker sibling (bge-reranker-v2-m3) is Apache 2.0. Both unrestricted.

What hardware do I need to run BGE-M3 (embeddings)?

CPU is fine. Any GPU is instant. Weights alone are roughly 0.5 GB at Q4_K_M and 0.8 GB at Q8_0. Add KV cache on top of that, which grows with your context length.

What licence is BGE-M3 (embeddings) released under?

MIT. Full commercial use. Shortest and least restrictive of the common licences; no explicit patent grant.

Where can I use BGE-M3 (embeddings) for free?

Free tiers carrying it include Hugging Face Inference Providers. Limits differ per provider and change often, so check each provider's own limits page. You can also self-host the weights, which has no rate limit at all.

Similar models

Wiring BGE-M3 (embeddings) into something real?

We build the evaluation harness, the failover and the cost ceilings around a model like this, so it survives contact with production.

Maps to AI strategy and consulting and AI automation development. Or see it working: our case studies.