InnerVault

Library

85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.

Results

670 results with any of your words Clear search and filters
  1. Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

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

    meta-llama/llama-4-scout
  2. Lynn

    Agents & frameworks

    开源桌面 AI Agent 与 CLI:长期记忆、多 Agent、实时语音;Qwen3.8-27B Coder390 EfficientThink 本地 GGUF(llama.cpp Q2/Q3,内置 Q4 MTP)· Open-source desktop AI agent & CLI with Coder390 local models

    Stale GitHub, MerkyorLynn 71 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/MerkyorLynn/Lynn.git
  3. 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
  4. 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
  5. 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 12 days ago

    kt/midm-k-3.0-pro
  6. 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
  7. *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

    Indexed OpenRouter model list, inclusionai Updated 3 months ago

    inclusionai/ling-3.0-flash
  8. gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-120b
  9. gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

    Indexed OpenRouter model list, openai Updated 12 months ago

    openai/gpt-oss-safeguard-20b
  10. gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-120b:batch
  11. Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-26b-a4b-it
  12. Z.ai: GLM 4.5

    Models

    GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

    Indexed OpenRouter model list, z-ai Updated 16 months ago

    z-ai/glm-4.5
  13. Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-26b-a4b-it:free
  14. GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

    Indexed OpenRouter model list, z-ai Updated 16 months ago

    z-ai/glm-4.5-air
  15. Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..

    Stale Official MCP Registry, com.modevc Updated 30 days ago 1 note

  16. GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

    Indexed OpenRouter model list, z-ai Updated 15 months ago

    z-ai/glm-4.5v
  17. qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.

    Stale Official MCP Registry, com.modevc Updated 30 days ago 1 note

  18. WireStudio

    MCP servers

    Agent-driven design studio for ESPHome-compatible (e.g. ESP32/ESP8266, RP2040) + LoRaWAN devices: generates ESPHome YAML, KiCad schematic/PCB, 3D-printable enclosures, and builds/flashes/provisions LoRaWAN firmware (ChirpStack + Home Assistant).

    Indexed GitHub, moellere 28 ★MITUpdated 3 days ago

    git clone https://github.com/moellere/WireStudio.git
  19. imp

    Agents & frameworks

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    Stale GitHub, kekzl 124 ★MITUpdated 13 days ago

    git clone https://github.com/kekzl/imp.git
  20. Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

    Indexed OpenRouter model list, prism-ml Updated 32 days ago

    prism-ml/ternary-bonsai-2-9b
  21. Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

    Indexed OpenRouter model list, prism-ml Updated 2 months ago

    prism-ml/ternary-bonsai-2-27b
  22. Act as a Test Automation Engineer. You are skilled in writing unit tests for TypeScript projects using Vitest. Your task is to guide developers on creating unit tests according to the RCS-001 standard. You will: -…

    Indexed prompts.chat (CC0 prompt collection), moein.zargarzadeh@gmail.com CC0-1.0

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.