Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
text generation model by kaushikvira · strata
kaushikvira/DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata -
text generation model by orcarouter · gguf
orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF -
image text to text model by nota-ai · transformers
nota-ai/Kimi-K3.1-Pro-Global-Pruned-30 -
image text to text model by nota-ai · transformers
nota-ai/Kimi-K3.1-Pro-Global-Pruned-37 -
janas
AI repositories37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
git clone https://github.com/prabanta-dev/janas.git -
nemotron-3.5-120b-cq
Modelsimage text to text model by Cactus-Compute · mlx
Cactus-Compute/nemotron-3.5-120b-cq -
Awesome-LLM-Ensemble
Agents & frameworksA curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble" (IJCAI Survey 2026)
git clone https://github.com/junchenzhi/Awesome-LLM-Ensemble.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 -
text generation model by DavidAU
DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF -
slotstream
AI repositoriesRun a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
git clone https://github.com/carloslfu/slotstream.git -
ipex-llm
AI repositoriesAccelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
git clone https://github.com/intel/ipex-llm.git -
MiniMax: MiniMax-01
ModelsMiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
minimax/minimax-01 -
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 -
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 -
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
nvidia/nemotron-3-nano-30b-a3b -
MoonshotAI: Kimi K2 0711
ModelsKimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
moonshotai/kimi-k2 -
Qwen: Qwen3 30B A3B
ModelsQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
qwen/qwen3-30b-a3b -
NVIDIA: Nemotron 3 Super
ModelsNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
nvidia/nemotron-3-super-120b-a12b -
NVIDIA: Nemotron 3 Ultra
ModelsNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b -
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 -
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b:free -
MoonshotAI: Kimi K2 Thinking
ModelsKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
moonshotai/kimi-k2-thinking -
MoonshotAI: Kimi K2 0905
ModelsKimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
moonshotai/kimi-k2-0905 -
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
tencent/hunyuan-a13b-instruct
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.