InnerVault

Library

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

Results

  1. VKORE-46M-NPU

    Models

    text generation model by FINAL-Bench · transformers

    Stale Hugging Face Hub, FINAL-Bench 27 ♥apache-2.0Updated 27 days ago

    FINAL-Bench/VKORE-46M-NPU
  2. text to image model by AuroraAI-Research · diffusers

    Stale Hugging Face Hub, AuroraAI-Research 24 ♥apache-2.0Updated 12 days ago

    AuroraAI-Research/AuroraIMG2-100M
  3. image text to text model by JonathanColetti · transformers

    Stale Hugging Face Hub, JonathanColetti 25 ♥apache-2.0Updated 9 days ago

    JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit
  4. model by mradermacher · transformers

    Indexed Hugging Face Hub, mradermacher 22 ♥apache-2.0Updated yesterday

    mradermacher/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic-GGUF
  5. image text to text model by Cactus-Compute · mlx

    Indexed Hugging Face Hub, Cactus-Compute 22 ♥otherUpdated 4 days ago 1 note

    Cactus-Compute/nemotron-3.5-120b-cq
  6. An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

    Indexed OpenRouter model list, mancer Updated 3 years ago

    mancer/weaver
  7. Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

    Indexed OpenRouter model list, qwen Updated 54 days ago

    qwen/qwen3.8-max-prime
  8. Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-max-0902
  9. Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-max-0902:batch
  10. Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

    Indexed OpenRouter model list, qwen Updated 5 months ago

    qwen/qwen3.7-max
  11. Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....

    Indexed OpenRouter model list, qwen Updated today

    qwen/qwen4-max
  12. Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

    Indexed OpenRouter model list, sakana Updated 2 months ago

    sakana/fugu-max
  13. Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

    Indexed OpenRouter model list, meta-llama Updated 19 months ago

    meta-llama/llama-4-maverick
  14. Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

    Indexed OpenRouter model list, thinkingmachines Updated 7 days ago

    thinkingmachines/inkling-2-small
  15. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

    Indexed OpenRouter model list, thinkingmachines Updated 3 months ago

    thinkingmachines/inkling-small
  16. Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

    Indexed OpenRouter model list, thinkingmachines Updated 7 days ago

    thinkingmachines/inkling-2-small:free
  17. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

    No longer listed OpenRouter model list, thinkingmachines Updated 3 months ago

    thinkingmachines/inkling-small:free
  18. Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

    Indexed OpenRouter model list, thinkingmachines Updated 4 months ago

    thinkingmachines/inkling
  19. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

    Indexed OpenRouter model list, thinkingmachines Updated 3 months ago

    thinkingmachines/inkling-small:batch
  20. Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

    No longer listed OpenRouter model list, thinkingmachines Updated 4 months ago

    thinkingmachines/inkling:free
  21. GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

    Indexed OpenRouter model list, openai Updated 11 months ago

    openai/gpt-5.1-codex-max
  22. Magnum v4 72B

    Models

    This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

    Indexed OpenRouter model list, anthracite-org Updated 2 years ago

    anthracite-org/magnum-v4-72b
  23. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

    Indexed OpenRouter model list, nvidia Updated 8 months ago

    nvidia/nemotron-3-super-120b-a12b
  24. GPT-6 Luna

    Models

    Focused, high-volume tasks where speed and running cost matter most.

    Indexed AETHER official model feed, OpenAI Updated 55 days ago

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.