Model reference · open weights

H0-mini

Embeddings bioptimus Image embed 1 build Non-commercial 6k dl/mo

H0-mini is an open-weight embedding model from bioptimus. H0-mini (FP32) weighs 171 MB; the smallest configuration that runs it is RTX 3060 12 GB.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • H0-mini is a lightweight foundation model for histology image feature extraction developed by Owkin and Bioptimus.
  • It is a Vision Transformer Base/14 with 86M parameters, distilled from H-optimus-0 using DINOv2 self-supervised distillation on 43 million histology tiles.
  • The model is licensed under cc-by-nc-nd-4.0.

Summary of the bioptimus/H0-mini model card, 2026-10-01

What it is

Released bybioptimus
Released2025-02-26
Parameters86M
VRAM171 MB for the weights

What it runs on

Memory and cards for H0-mini (FP32)

171 MBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

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, which is the basis of search and RAG.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms