Model reference · open weights

MegaLoc

MegaLoc is an open-weight embedding model from gberton, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings gberton 1 variants 97k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What MegaLoc is

MegaLoc MegaLoc is an image retrieval model for visual place recognition (VPR) that achieves state-of-the-art on most VPR datasets, including indoor and outdoor environments. Paper: MegaLoc: One Retrieval to Place Them All (CVPR 2025 Workshop) GitHub: gmberton/MegaLoc Usage For benchmarking on VPR datasets, see VPR-methods-evaluation. Qualitative Examples Top-1 retrieved images from the SF-XL test set (2.8M database images): Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makergberton
TypeEmbedding models
Parameters (lead)229M
Variants1
Runs withpytorch
Released2025-02-27
Popularity97k downloads / month
Likes10
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
MegaLoc229MBF16~0.5 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys megaloc for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (megaloc below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"megaloc","input":"text to embed"}'

Details

Languages, data & research

Tags

pytorch safetensors megaloc visual-place-recognition image-retrieval image-feature-extraction

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want MegaLoc on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

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