Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pegainfer
AI repositoriesPure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
git clone https://github.com/pegainfer-project/pegainfer.git -
Apex-35B-V1.0
Modelstext generation model by Apexintelligence-AI · transformers
Apexintelligence-AI/Apex-35B-V1.0 -
Ornith-1.5-122B-NVFP4
Modelstext generation model by ornith-ai · transformers
ornith-ai/Ornith-1.5-122B-NVFP4 -
NorthCUA-Pro
Modelsimage text to text model by beipo-ai · transformers
beipo-ai/NorthCUA-Pro -
JEV-35B-NVFP4
Modelstext classification model by autotrust · transformers
autotrust/JEV-35B-NVFP4 -
image text to text model by jackjusko · gguf
jackjusko/Swift-1.5-Flash-Next-Heretic-ReverseEngineer -
image text to text model by trubisky · gguf
trubisky/Swift-1.5-Flash-Next-Heretic-ReverseEngineer -
Whittle-Next-27B-A3B
Modelstext generation model by whittleOrg · transformers
whittleOrg/Whittle-Next-27B-A3B -
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 -
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 -
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 -
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 -
Qwen: Qwen3 Coder 480B A35B
ModelsQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
qwen/qwen3-coder -
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 -
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 -
Omni-Image-Editor
Tools & appsHugging Face space by selfit-camera
selfit-camera/Omni-Image-Editor -
Omni-Video-Factory
Tools & appsHugging Face space by FrameAI4687
FrameAI4687/Omni-Video-Factory -
Qwen2.5-Omni-7B
Modelsany to any model by Qwen · transformers
Qwen/Qwen2.5-Omni-7B -
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 -
LFM3-Omni-2B
Modelsany to any model by LiquidAI · transformers
LiquidAI/LFM3-Omni-2B -
Llama-3.1-8B-Omni
Modelsmodel by ICTNLP · llama-omni
ICTNLP/Llama-3.1-8B-Omni -
mini-omni
Modelstext to speech model by gpt-omni
gpt-omni/mini-omni -
Qwen2.5-Omni-3B
Modelsany to any model by Qwen · transformers
Qwen/Qwen2.5-Omni-3B -
FastH3-Omni-Comfy
Modelsmodel by FastVideo · diffusion-single-file
FastVideo/FastH3-Omni-Comfy
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.