The request names siglip2-large-patch16-256, a SigLIP 2 vision-language model. The closest match in the sources is an image-embedding model on Replicate (siglip-large-patch16-384, a sibling variant at a different input resolution), which can produce embeddings from images; the exact 256 variant is not shown on the cited pages.
- 1
- 2
SGLangsglang.iowebsite read, tools not yet checked
Open-source serving framework for large language, vision-language and diffusion models, which can host a SigLIP 2 model for self-hosted inference 4.
+2 community tools built for it
- 3
fast.aifast.aiverified and signed
Deep learning library and course for PyTorch, which can load and fine-tune pretrained vision models of this kind 3.
+462 community tools built for it
for agents: python · api · github
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 3fast.ai—Making neural nets uncool again – fast.aifast.ai · read 2026-10-29
- 4SGLang – Fast, Open-Source LLM & Multimodal Serving Frameworksglang.io · read 2026-10-29
- 5devarsh-mavani-19/siglip-large-patch16-384: declares "devarsh-mavani-19/siglip-large-patch16-384" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
devarsh-mavani-19/siglip-large-patch16-384 · devarsh-mavani-19/siglip-large-patch16-384 verified and signed
Get embeddings for image using siglip-large-patch16-384
varad-13/siglip-2-large · varad-13/siglip-2-large verified and signed
create-llms · create-llms verified and signed
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
lucataco/siglip · lucataco/siglip verified and signed
SigLIP proposes to replace the loss function used in CLIP by a simple pairwise sigmoid loss
adirik/bunny-phi-2-siglip · adirik/bunny-phi-2-siglip verified and signed
Lightweight multimodal model for visual question answering, reasoning and captioning
python · fastcore verified and signed
cjwbw/clip-vit-large-patch14 · cjwbw/clip-vit-large-patch14 verified and signed
openai/clip-vit-large-patch14 with Transformers
· SGLang website read, tools not yet checked
SGLang powers fast, scalable inference for large language and multimodal models. Open-source serving framework with state-of-the-art performance.
lucataco/llama-3-vision-alpha · lucataco/llama-3-vision-alpha verified and signed
Projection module trained to add vision capabilties to Llama 3 using SigLIP
lucataco/qwen3-vl-8b-instruct · lucataco/qwen3-vl-8b-instruct verified and signed
A powerful vision-language model in the Qwen series
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.