Model reference · open weights

siglino-moe-0.15

siglino-moe-0.15 is an open-weight embedding model from tiiuae, 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 tiiuae 1 variants 110 downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What siglino-moe-0.15 is

SigLino-MoE-0.15-0.6B Accepted at CVPR 2026 [](https://sofianchay.github.io/siglino/) [](https://arxiv.org/abs/2512.20157) [](https://github.com/tiiuae/siglino) This work stems from the CVPR 2026 AMoE paper, which designs and applies distillation into a Mixture-of-Experts (MoE) vision architecture. We have chosen the name SigLino for better clarity (SigLIP2 + DINOv3). Ultra-sparse MoE variant of SigLino with top-2 out of 28 experts routing. 0.15B active parameters, 0.6B total. Part of the SigLino model family. Usage Model Details Results (512x512, ensemble features) Citation

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

Specifications

What it is

Makertiiuae
TypeEmbedding models
Parameters (lead)523M
Context8k tokens
Variants1
Runs withtransformers
Released2026-03-11
Popularity110 downloads / month
Likes8
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
siglino-moe-0.15-0.6B523MBF16~1.2 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys siglino-moe-0-15 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (siglino-moe-0-15 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":"siglino-moe-0-15","input":"text to embed"}'

Details

Languages, data & research

Tags

transformers safetensors siglino feature-extraction vision image-feature-extraction custom_code

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want siglino-moe-0.15 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