Library
85,843 resources from 11 public sources. 51 checked by hand; the rest are unreviewed.
Results
-
MiMo-V2.6-Pro-RL
Modelstext generation model by XiaomiMiMo · transformers
XiaomiMiMo/MiMo-V2.6-Pro-RL -
UI-TARS-1.5-7B
Modelsimage text to text model by ByteDance-Seed · transformers
ByteDance-Seed/UI-TARS-1.5-7B -
InternVL-Chat-V1-5
Modelsimage text to text model by OpenGVLab · transformers
OpenGVLab/InternVL-Chat-V1-5 -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
vllm-mlx
AI repositoriesHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
git clone https://github.com/waybarrios/vllm-mlx.git -
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
qwen/qwen3-coder-30b-a3b-instruct -
HY-Embodied-0.5
Modelsimage text to text model by tencent · transformers
tencent/HY-Embodied-0.5 -
HunyuanOCR
Modelsimage text to text model by tencent · transformers
tencent/HunyuanOCR -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.git -
MiniCPM-V-4.7-1B
Modelsimage text to text model by openbmb · transformers
openbmb/MiniCPM-V-4.7-1B -
Mage-VL
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL -
Step-3.7-Flash
Modelsimage text to text model by stepfun-ai · transformers
stepfun-ai/Step-3.7-Flash -
image text to text model by HauhauCS
HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive -
MedXpertQA
Datasets & benchmarks[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
git clone https://github.com/TsinghuaC3I/MedXpertQA.git -
MiniMax-M3.1-Flash
Modelsimage text to text model by MiniMaxAI · transformers
MiniMaxAI/MiniMax-M3.1-Flash -
opendroid
AI repositoriesYour Open Autonomous Android Agent — A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.
git clone https://github.com/JMAN730/opendroid.git -
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
qwen/qwen3-235b-a22b-thinking-2507 -
RAG-Survey
AI repositoriesCollecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".
git clone https://github.com/hymie122/RAG-Survey.git -
Kimi-VL-A3B-Thinking-2506
Modelsimage text to text model by moonshotai · transformers
moonshotai/Kimi-VL-A3B-Thinking-2506 -
MiniCPM-V-4
Modelsimage text to text model by openbmb · transformers
openbmb/MiniCPM-V-4 -
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 -
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
qwen/qwen3-30b-a3b-instruct-2507 -
Qwen2-VL-72B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen2-VL-72B-Instruct -
LongCat-2.5
Modelsimage text to text model by meituan-longcat
meituan-longcat/LongCat-2.5
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.