Dedicated model · Available as managed deployment

Request a BGE-M3 deployment on your own DGX Spark

BAAI's BGE-M3 — a multilingual embedding model with dense, sparse and multi-vector retrieval in one, an 8,192-token input window, under MIT. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.

eu-es-1 · Málaga Available as managed deployment 8,194 ctx · Text → vector (embeddings) Quoted per deployment bge-m3.axforge.ai
Request deploymentTalk to an engineerSign in €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT Hardware rental plus a managed service quoted per deployment — both confirmed in writing before anything is billed.

Why AxForge

Why BGE-M3 as a managed deployment

Three retrieval modes in oneDense vectors, sparse lexical weights and ColBERT-style multi-vectors from a single model — hybrid search without three models.
100+ languages, 8k tokensLong documents and multilingual corpora embedded in one pass.
MIT licencePermissive — commercial use, no licence conversation.

Specifications

What you get

ModelBGE-M3 — BAAI
ModalitiesText → vector (embeddings)
Context window8,194 tokens
LicenceOpen weights — mit; commercial use permitted
HardwareNVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge
Rental termHour, week, month or year
Hardware pricing€0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT
Managed serviceQuoted per deployment
RegionMálaga, Spain (eu-es-1)

Full details, benchmarks and FAQ on the BGE-M3 page. Prices exclude VAT.

How it works

From sign-in to running

1Request deployment — describe your traffic, context needs and rental term.
2You receive the configuration, hardware rental and managed-service price in writing before anything is billed.
3AxForge deploys BGE-M3 on a dedicated DGX Spark reserved for you.
4Point your OpenAI SDK at your own endpoint with the model name you receive.
5Adjust the term — hour, week, month or year — as your workload settles.

Request deployment or sign in to start.

FAQ

BGE-M3 — common questions

Is BGE-M3 on the AxForge serverless API?

Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.

BGE-M3 or Qwen3 Embedding on the serverless API?

Qwen3 Embedding is what AxForge serves per token; BGE-M3 is the choice for a dedicated deployment when you want hybrid (dense + sparse) retrieval or its multilingual coverage.

What does a dedicated embedding deployment look like?

A dedicated DGX Spark embedding your documents behind an OpenAI-compatible /v1/embeddings endpoint — millions of chunks a day, in the EU.

How fast is it on your hardware?

AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.

What does EU BGE-M3 hosting cost?

Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.

Ready for BGE-M3 on your own machine?

Request deployment Sign in Talk to an engineer

Explore

More from AxForge

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms