InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. text generation model by Scantist

    Indexed Hugging Face Hub, Scantist 1,423 ♥otherUpdated 13 days ago

    Scantist/GLM-5.3-SLIM-GGUF
  2. image text to text model by autotrust · vllm

    Stale Hugging Face Hub, autotrust 561 ♥mitUpdated 36 days ago

    autotrust/GLM5.3-Flash-E224-DGX-Spark
  3. image text to text model by autotrust · vllm

    Stale Hugging Face Hub, autotrust 180 ♥mitUpdated 36 days ago

    autotrust/GLM5.3-Flash-E192-DGX-Spark
  4. image text to text model by autotrust · vllm

    Stale Hugging Face Hub, autotrust 118 ♥mitUpdated 36 days ago

    autotrust/GLM5.3-Flash-E256-DGX-Spark
  5. Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

    Indexed OpenRouter model list, qwen Updated 18 months ago

    qwen/qwen3-30b-a3b
  6. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b
  7. Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

    No longer listed OpenRouter model list, stepfun Updated 9 months ago

    stepfun/step-3.5-flash
  8. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b:free
  9. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    Indexed OpenRouter model list, moonshotai Updated 12 months ago

    moonshotai/kimi-k2-thinking
  10. MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

    No longer listed OpenRouter model list, minimax Updated 17 months ago

    minimax/minimax-m1
  11. DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

    Indexed OpenRouter model list, deepseek Updated 13 months ago

    deepseek/deepseek-v3.2-exp
  12. Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

    Indexed OpenRouter model list, meta-llama Updated 2 years ago

    meta-llama/llama-3.2-3b-instruct
  13. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

    Indexed OpenRouter model list, stepfun Updated 39 days ago

    stepfun/step-5-preview
  14. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-20b
  15. 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
  16. Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

    Indexed OpenRouter model list, kt Updated 11 days ago

    kt/midm-k-3.0-pro
  17. Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/mistral-large-2512
  18. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-20b:batch
  19. Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

    Indexed OpenRouter model list, reflection Updated 31 days ago

    reflection/beam-1.0-501b-a23b
  20. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

    Indexed OpenRouter model list, deepseek Updated 2 months ago

    deepseek/deepseek-v4.1-flash
  21. 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
  22. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

    Indexed OpenRouter model list, deepseek Updated 2 months ago

    deepseek/deepseek-v4.1-flash:batch
  23. Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

    Indexed OpenRouter model list, qwen Updated 7 months ago

    qwen/qwen3.6-plus
  24. Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-9b

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.