Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
NuMarkdown-8B-Thinking
Modelsimage to text model by numind · transformers
numind/NuMarkdown-8B-Thinking -
Nemotron-3.5-Embed-8B-BF16
Modelsvisual document retrieval model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Embed-8B-BF16 -
MiniCPM-OCR-1.0
Modelsimage text to text model by openbmb · minicpm-ocr
openbmb/MiniCPM-OCR-1.0 -
PaddleOCR-VL-1.5
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.5 -
PaddleOCR-VL-1.6
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.6 -
Youtu-Parsing-Omni
Modelsimage text to text model by tencent · transformers
tencent/Youtu-Parsing-Omni -
meta-encoder-v1
Modelsfeature extraction model by facebook · transformers
facebook/meta-encoder-v1 -
LightOnOCR-3-4B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-4B -
MiniCPM-OCR-1.0-gguf
Modelsimage text to text model by openbmb
openbmb/MiniCPM-OCR-1.0-gguf -
OvisOCR3
Modelsimage text to text model by ATH-MaaS · transformers
ATH-MaaS/OvisOCR3 -
OpenThai2.0-OCR-Markdown
Modelsimage text to text model by iapp
iapp/OpenThai2.0-OCR-Markdown -
unlimited-ocr-mlx-coreml
Modelsimage text to text model by FluidInference · mlx
FluidInference/unlimited-ocr-mlx-coreml -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Cactus-Compute/mirage -
GroundAnything-VLM
Modelsimage text to text model by GroundingPI · transformers
GroundingPI/GroundAnything-VLM -
LightOnOCR-3-1B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-1B -
GroundingPI
Modelsimage text to text model by GroundingPI · transformers
GroundingPI/GroundingPI -
Nemotron-3.5-Rerank-8B-BF16
Modelstext ranking model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Rerank-8B-BF16 -
GPT-6 Astra
ModelsThe most demanding work: complex reasoning, research, computer use and document creation.
-
Claude Sonnet 5.5
ModelsEveryday business work: fixing bugs and drafting polished documents, slides and spreadsheets.
-
Claude Opus 5.5
ModelsLong, sprawling jobs: large sets of documents, audits and changes across a whole codebase.
-
Gemini 4 Hydrogen
ModelsFast, low-cost help for everyday coding and agent workflows, with room for very long documents.
-
ScaleDown: Summarize
ModelsSummarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
scaledown/summarize -
Upstage: Solar Pro 4
ModelsSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...
upstage/solar-pro4 -
Qwen: Qwen3.8 Flash
ModelsQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
qwen/qwen3.8-flash
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.