Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Qwen3.8-35B-A3B-Distill-GGUF
Modelstext generation model by empero-ai · gguf
empero-ai/Qwen3.8-35B-A3B-Distill-GGUF -
Tiel-Coder-35B-A3B-GGUF
Modelsimage text to text model by peculiar-ragdoll · gguf
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF -
text generation model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 -
text generation model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 -
text generation model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 -
image to video model by Abiray · minimax-h3
Abiray/Minimax-h3-Singularity-V2-Pruned -
aiquant-lite
Agents & frameworksAI 原生 A 股投研中枢|百万级本地数据 × 量化实验 × 多模型研究 × 可追溯决策。Research deeper. Decide with evidence. · Local-first · Hermes / MCP.
git clone https://github.com/Shixi216/aiquant-lite.git -
image to video model by WAS · minimax-h3
WAS/Minimax-h3_Singularity_v2_pruned -
image text to text model by SC117 · gguf
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF -
text generation model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 -
deepseek-v4-gguf
Modelstext generation model by antirez · gguf
antirez/deepseek-v4-gguf -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
ms-swift
AI repositoriesUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
git clone https://github.com/modelscope/ms-swift.git -
tools
AI repositoriesA set of tools that gives agents powerful capabilities.
git clone https://github.com/strands-agents/tools.git -
LongBench
Datasets & benchmarksLongBench v2 and LongBench (ACL 25'&24')
git clone https://github.com/THUDM/LongBench.git -
director-mode-lite
SkillsUse Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.
git clone https://github.com/claude-world/director-mode-lite.git -
claude-code-settings
SkillsCurated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.
git clone https://github.com/feiskyer/claude-code-settings.git -
GLM5.3-Flash-E224-DGX-Spark
Modelsimage text to text model by autotrust · vllm
autotrust/GLM5.3-Flash-E224-DGX-Spark -
Sage-A1.5-Q4_K_M-GGUF
Modelstext generation model by InternScience · gguf
InternScience/Sage-A1.5-Q4_K_M-GGUF -
Liters/min to liters/s, number discarded
MCP serversLiters/min to liters/s, number discarded
-
Agentero
Agents & frameworksUnified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台;补齐 Zotero 时代的人机上下文断点。
git clone https://github.com/poco-ai/Agentero.git -
text generation model by LibertAIDAI
LibertAIDAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw -
Naive-N0.5-Flash-FP8
Modelstext generation model by NaiveAI
NaiveAI/Naive-N0.5-Flash-FP8 -
Tiel-Coder-35B-A3B-GGUF-MTP
Modelsimage text to text model by peculiar-ragdoll · gguf
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
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.