InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

1,074 results Clear search and filters
  1. Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

    Indexed OpenRouter model list, moondream Updated 33 days ago

    moondream/moondream3.1-9b-a2b
  2. iris-3b

    Models

    text to image model by speridlabs · pytorch

    Stale Hugging Face Hub, speridlabs 328 ♥apache-2.0Updated 36 days ago

    speridlabs/iris-3b
  3. image to text model by microsoft · transformers

    Stale Hugging Face Hub, microsoft 528 ♥mitUpdated 21 months ago

    microsoft/trocr-base-handwritten
  4. text generation model by XiaomiMiMo · transformers

    Stale Hugging Face Hub, XiaomiMiMo 582 ♥mitUpdated 39 days ago

    XiaomiMiMo/MiMo-V2.6-Flash-RL
  5. The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-flash-02-23
  6. Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

    Indexed OpenRouter model list, anthropic Updated 8 days ago

    anthropic/claude-fable-5.2
  7. The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-35b-a3b
  8. The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-122b-a10b
  9. The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3.5-397b-a17b
  10. Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

    Indexed OpenRouter model list, anthropic Updated 8 days ago

    anthropic/claude-fable-5.2:batch
  11. Qwen3.8-27B

    Models

    image text to text model by Qwen · transformers

    Indexed Hugging Face Hub, Qwen 20.2k ♥apache-2.0Updated 10 days ago

    Qwen/Qwen3.8-27B
  12. The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3.5-plus-02-15
  13. image to text model by numind · transformers

    Stale Hugging Face Hub, numind 497 ♥mitUpdated 5 months ago

    numind/NuMarkdown-8B-Thinking
  14. Agents-A1

    Models

    text generation model by InternScience · transformers

    Stale Hugging Face Hub, InternScience 652 ♥apache-2.0Updated 57 days ago

    InternScience/Agents-A1
  15. image text to text model by Qwen · transformers

    Indexed Hugging Face Hub, Qwen 7,179 ♥otherUpdated 10 days ago

    Qwen/Qwen3.8-Flash-Next
  16. image text to text model by google · transformers

    Indexed Hugging Face Hub, google 4,380 ♥apache-2.0Updated 4 months ago

    google/gemma-4-31B-it
  17. NuExtract3

    Models

    image to text model by numind · transformers

    Stale Hugging Face Hub, numind 377 ♥apache-2.0Updated 2 months ago

    numind/NuExtract3
  18. Kimi-K3

    Models

    image text to text model by moonshotai · transformers

    Indexed Hugging Face Hub, moonshotai 12.0k ♥otherUpdated 2 months ago

    moonshotai/Kimi-K3
  19. image text to text model by google

    Indexed Hugging Face Hub, google 1,504 ♥gemmaUpdated 18 months ago 1 note

    google/gemma-3n-E4B-it-litert-preview
  20. image text to text model by unsloth

    Indexed Hugging Face Hub, unsloth 1,767 ♥otherUpdated 4 days ago

    unsloth/Qwen3.8-Flash-Next-GGUF
  21. fuyu-8b

    Models

    image text to text model by adept · transformers

    Stale Hugging Face Hub, adept 1,026 ♥cc-by-nc-4.0Updated 3 years ago

    adept/fuyu-8b
  22. OmniParser

    Models

    image text to text model by microsoft · transformers

    Indexed Hugging Face Hub, microsoft 1,719 ♥mitUpdated 23 months ago

    microsoft/OmniParser
  23. Qwen3.5-9B

    Models

    image text to text model by Qwen · transformers

    Indexed Hugging Face Hub, Qwen 2,380 ♥apache-2.0Updated 8 months ago

    Qwen/Qwen3.5-9B
  24. Qwen3.6-27B

    Models

    image text to text model by Qwen · transformers

    Indexed Hugging Face Hub, Qwen 2,354 ♥apache-2.0Updated 10 days ago

    Qwen/Qwen3.6-27B

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.