Model reference · open weights
naflexvit_so400m_patch16_siglip.v2_webli is an open-weight embedding model from timm, 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.
About
Model card for naflexvitso400mpatch16siglip.v2webli SigLIP-2 (https://arxiv.org/abs/2502.14786) SO400M/16 NaFlex ViT encoder weights for timm NaFlexViT
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | timm |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 428M |
| Variants | 1 |
| Runs with | timm |
| Released | 2025-08-04 |
| Popularity | 124k downloads / month |
| Likes | 1 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| naflexvit_so400m_patch16_siglip.v2_webli | 428M | BF16 | ~1 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys naflexvit-so400m-patch16-siglip-v2-webli for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (naflexvit-so400m-patch16-siglip-v2-webli 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":"naflexvit-so400m-patch16-siglip-v2-webli","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore