Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
text to video model by Veda-Sparse · minimax-h3
Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview -
Minimax-H3-R2VA-Veda-Preview
Modelstext to video model by Veda-Sparse · minimax-h3
Veda-Sparse/Minimax-H3-R2VA-Veda-Preview -
Prism
Modelsimage to video model by FrancisRing · diffusers
FrancisRing/Prism -
nncf
AI repositoriesNeural Network Compression Framework for enhanced OpenVINO™ inference
git clone https://github.com/openvinotoolkit/nncf.git -
cuvs
AI repositoriescuVS - a library for vector search and clustering on the GPU
git clone https://github.com/NVIDIA/cuvs.git -
Thinklite-27B
Modelsimage text to text model by Sparset · transformers
Sparset/Thinklite-27B -
NextTransformer
Datasets & benchmarks:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
git clone https://github.com/Interactive-Active-AI/NextTransformer.git -
rag-experiment-accelerator
AI repositoriesThe RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
git clone https://github.com/microsoft/rag-experiment-accelerator.git -
raft
AI repositoriesRAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
git clone https://github.com/NVIDIA/raft.git -
SparkVSR
AI repositories[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
git clone https://github.com/taco-group/SparkVSR.git -
DeepSeek: DeepSeek V3.2
ModelsDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2 -
DeepSeek: DeepSeek V3.2 Exp
ModelsDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2-exp -
Baidu: ERNIE-Light-DT-1.0
ModelsERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...
baidu/ernie-light-dt-1.0-intl -
infinity
AI repositoriesThe AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
git clone https://github.com/infiniflow/infinity.git -
ResiMind
MCP serversExact polynomial checks, sparse expansion and verified rule memory. Local MCP tools, no model key.
https://github.com/1105216375-alt/resimind/releases/download/v0.16.0/resimind-0.16.0.mcpb -
Qwen: Qwen3 Coder Next
ModelsQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
qwen/qwen3-coder-next -
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
cohere/north-mini-code:free -
StepFun: Step 3.5 Flash
ModelsStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
stepfun/step-3.5-flash -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731 -
Meituan: LongCat 2.0
ModelsLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
meituan/longcat-2.0 -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731:batch -
StepFun: Step 5 Preview
ModelsStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
stepfun/step-5-preview -
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
mistralai/mistral-large-2512 -
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
reflection/beam-1.0-501b-a23b
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.