Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pplx-decider-flash-v1.2
Modelstext classification model by perplexity-ai · pytorch
perplexity-ai/pplx-decider-flash-v1.2 -
Qwopus3.5-27B-v3-GGUF
Modelsimage text to text model by Jackrong · transformers
Jackrong/Qwopus3.5-27B-v3-GGUF -
LemonDecider
Modelsfeature extraction model by inclusionAI · transformers
inclusionAI/LemonDecider -
drex-max-v1
Modelszero shot classification model by nace-ai · pytorch
nace-ai/drex-max-v1 -
Xiaomi-OCR-0
Modelsimage text to text model by xiaomi-research · transformers
xiaomi-research/Xiaomi-OCR-0 -
Octen-WebGR-4B
Modelstext generation model by Octen · transformers
Octen/Octen-WebGR-4B -
h2o-lightning-4b
Modelsimage text to text model by h2oai · transformers
h2oai/h2o-lightning-4b -
d3-turbo
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-turbo -
AesCode-8B
Modelsimage text to text model by microsoft · transformers
microsoft/AesCode-8B -
TVPulse
MCP serversSearch OCR/ASR mentions on 15 terrestrial stations (Tokyo 7, Osaka 8); archive from 2026-01-01.
-
DeepSeek Web Search
MCP serversMCP server for DeepSeek tools: scored web search, page-to-Markdown fetch, OCR, ASR and TTS
mcp-deepseek-search@1.1.0 -
Qwopus3.5-9B-Coder-GGUF
Modelsimage text to text model by Jackrong · transformers
Jackrong/Qwopus3.5-9B-Coder-GGUF -
pplx-embed-v2-late-0.6b
Modelsfeature extraction model by perplexity-ai · sentence-transformers
perplexity-ai/pplx-embed-v2-late-0.6b -
pplx-decider-v1.2
Modelstext classification model by perplexity-ai · pytorch
perplexity-ai/pplx-decider-v1.2 -
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 -
pplx-decider-flash-v1.3
Modelstext classification model by perplexity-ai · pytorch
perplexity-ai/pplx-decider-flash-v1.3 -
LightOnOCR-3-4B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-4B -
Apex-35B-V1.0
Modelstext generation model by Apexintelligence-AI · transformers
Apexintelligence-AI/Apex-35B-V1.0 -
Qwopus3.6-27B-v2-MTP-GGUF
Modelsimage text to text model by Jackrong · transformers
Jackrong/Qwopus3.6-27B-v2-MTP-GGUF -
Octen-WebGR-0.6B
Modelstext generation model by Octen · transformers
Octen/Octen-WebGR-0.6B -
Qwopus3.6-27B-Coder-MTP-GGUF
Modelsimage text to text model by Jackrong · transformers
Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF -
MiniMax-H3-Image-PE
Modelstext generation model by MiniMaxAI · transformers
MiniMaxAI/MiniMax-H3-Image-PE -
d3-flash
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-flash -
unsloth
AI repositoriesLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
git clone https://github.com/unslothai/unsloth.git
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.