Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
multimodal
MCP serversMulti-provider media generation — images, video, audio, and transcription via a unified interface
@r16t/multimodal-mcp@1.3.1 -
Nemotron-3.5-Embed-1B-NVFP4
Modelsvisual document retrieval model by nvidia · vllm
nvidia/Nemotron-3.5-Embed-1B-NVFP4 -
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
qwen/qwen3-vl-30b-a3b-instruct -
OpenAI: GPT-5.4 Image 2
Models[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...
openai/gpt-5.4-image-2 -
image text to text model by DavidAU
DavidAU/Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF -
image text to text model by DavidAU
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF -
Nemotron-3.5-Embed-8B-BF16
Modelsvisual document retrieval model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Embed-8B-BF16 -
Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
Modelsimage text to text model by DavidAU
DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF -
pdf4vllm
MCP serversPDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
pdf4vllm-mcp@1.0.2 -
Vision-Agents
Agents & frameworksOpen Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
git clone https://github.com/GetStream/Vision-Agents.git -
Elorian: Glimpse
ModelsGlimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
elorian/glimpse -
Mistral: Mistral Large 4
ModelsMistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
mistralai/mistral-large-4-0 -
inference
AI repositoriesOpen-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
git clone https://github.com/xorbitsai/inference.git -
Amazon: Nova Lite 1.0
ModelsAmazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
amazon/nova-lite-v1 -
Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers
git clone https://github.com/alphaparkinc/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git -
pardesline
MCP servers3D vision and medical imaging: 43 datasets with licences, 73 algorithms on clouds, meshes, CT/MRI
pardesline@0.5.0 -
mlx-vlm
AI repositoriesMLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
git clone https://github.com/Neywa-Labs/mlx-vlm.git -
MiniMax: MiniMax M3
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3 -
Qwen: Qwen3.6 27B
ModelsQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
qwen/qwen3.6-27b -
Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers
git clone https://github.com/Alpha-Park/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git -
Google: Gemma 4 31B
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it -
MiniMax: MiniMax M3 (batch)
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3:batch -
dsh-video-storyboard
Agents & frameworksScene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
git clone https://github.com/SAOS-3624/dsh-video-storyboard.git -
Pareto 26.9
ModelsPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
unbiased/pareto-26.9
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.