Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Awesome-LLMs-meet-Multimodal-Generation
AI repositories🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).
git clone https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation.git -
Qwen3.5-4B-heretic
Modelsimage text to text model by saidutta69 · transformers
saidutta69/Qwen3.5-4B-heretic -
agent-vision-toolkit
Skills为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
git clone https://github.com/Anionex/agent-vision-toolkit.git -
GPA-LM
Agents & frameworksThis repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".
git clone https://github.com/BAAI-Agents/GPA-LM.git -
star-vector
AI repositoriesStarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.
git clone https://github.com/joanrod/star-vector.git -
imnotarobot
MCP serversI am not a robot — a captcha solver for macOS: local model, Gemini vision, a stealth browser for checkbox captchas, RuCaptcha as the last resort. 2Captcha-compatible API and an MCP server.
git clone https://github.com/zigansh1n/imnotarobot.git -
ai-hardware-fit
Datasets & benchmarksCan my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.
git clone https://github.com/jaeseok614/ai-hardware-fit.git -
ARIS-in-AI-Offer
AI repositoriesBilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git -
Google: Gemma 3 4B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-4b-it -
Google: Gemma 3 12B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-12b-it -
Google: Gemma 3 27B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-27b-it -
Reka Edge
ModelsReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
rekaai/reka-edge -
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
moondream/moondream3-preview -
Perceptron: Perceptron Mk1
ModelsPerceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...
perceptron/perceptron-mk1 -
Qwen: Qwen3.5-27B
ModelsThe Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...
qwen/qwen3.5-27b -
Moondream: Moondream 3.1
ModelsMoondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
moondream/moondream3.1-9b-a2b -
Qwen: Qwen3.7 Flash
ModelsQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
qwen/qwen3.7-flash -
ByteDance: UI-TARS 7B
ModelsUI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
bytedance/ui-tars-1.5-7b -
Qwen: Qwen3.8 27B
ModelsQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b -
Qwen: Qwen3.5-Flash
ModelsThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
qwen/qwen3.5-flash-02-23 -
Qwen: Qwen3.5-9B
ModelsQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
qwen/qwen3.5-9b -
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
qwen/qwen3-vl-235b-a22b-instruct -
Qwen: Qwen3.8 27B (batch)
ModelsQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b:batch -
Qwen: Qwen3.5-35B-A3B
ModelsThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
qwen/qwen3.5-35b-a3b
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.