7 results
- LLaVA (Large Language-and-Vision Assistant) Featuredvision-multimodalPioneering open-source vision-language model enabling visual question answering and image captioning with local LLMs.Low setupCPU OnlyCommercial useApache 2.0★ 22kUpdated 2mo ago
- DeepSeek-VL2vision-multimodalEfficient open-source vision-language model with MoE architecture for scientific reasoning and edge-ready deployment.Low setupCPU OnlyCommercial useMIT★ 4.5kUpdated 1mo ago
- Falcon 2 VLMvision-multimodalTechnology Innovation Institute open-source vision-language model with fine detail recognition and multilingual support.Medium setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 3.8kUpdated 3mo ago
- InternVL3 (Shanghai AI Lab)vision-multimodalOpen-source vision-language model with 3D reasoning and top multimodal benchmark scores for complex visual tasks.Low setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 8.5kUpdated 1mo ago
- Phi-3-Vision (Microsoft)vision-multimodalMicrosoft compact multimodal model combining vision and language reasoning for edge device deployment.Low setupCPU OnlyCommercial useMIT★ 971Updated 6mo ago
- Pixtral 12B (Mistral AI)vision-multimodalMistral open-weight vision-language model with multi-image input and native resolution processing under Apache 2.0.Medium setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 689Updated 10mo ago
- Qwen2.5-VL (Alibaba)vision-multimodalOpen-source vision-language model with video support, object localization, and 29-language understanding under Apache 2.0.Medium setupCPU OnlyCommercial useApache 2.0★ 12kUpdated 28d ago
Offgrid AI tools · Updated daily
Enclavetools
Stop paying for AI APIs. Everything here runs on your hardware.
Sponsor
Reach 50,000+ enterprise buyers looking for private AI solutions.
Newsletter
5 new tools, every Friday
No fluff. No spam. Join 12,000+ builders.
Get featured
Put your tool at the top
Featured listings get 10× more clicks and are shown prominently across the directory.
Page 1 of 1