Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LightOnOCR-3-4B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-4B -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Cactus-Compute/mirage -
OvisOCR3
Modelsimage text to text model by ATH-MaaS · transformers
ATH-MaaS/OvisOCR3 -
Nemotron-3.5-Embed-8B-BF16
Modelsvisual document retrieval model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Embed-8B-BF16 -
Nemotron-3.5-Embed-1B-NVFP4
Modelsvisual document retrieval model by nvidia · vllm
nvidia/Nemotron-3.5-Embed-1B-NVFP4 -
MiniCPM-OCR-1.0-gguf
Modelsimage text to text model by openbmb
openbmb/MiniCPM-OCR-1.0-gguf -
meta-encoder-v1
Modelsfeature extraction model by facebook · transformers
facebook/meta-encoder-v1 -
LightOnOCR-3-0.8B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-0.8B -
OpenThai2.0-OCR-Markdown
Modelsimage text to text model by iapp
iapp/OpenThai2.0-OCR-Markdown -
GroundAnything-VLM
Modelsimage text to text model by GroundingPI · transformers
GroundingPI/GroundAnything-VLM -
unlimited-ocr-mlx-coreml
Modelsimage text to text model by FluidInference · mlx
FluidInference/unlimited-ocr-mlx-coreml -
Nemotron-3.5-Rerank-8B-BF16
Modelstext ranking model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Rerank-8B-BF16 -
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 -
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 -
Meta: Muse Wonder
ModelsMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
meta/muse-wonder -
OpenAI: GPT-6 Astra
ModelsGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
openai/gpt-6-astra -
Meta: Muse Spark 1.2
ModelsMuse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....
meta/muse-spark-1.2
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.