全站搜索

AI 模型 85003

• Hunyuan-3D-2.0↗

  Comfy-Org

  - https://huggingface.co/tencent/Hunyuan3D-2 - https://huggingface.co/tencent/Hunyuan3D-2mv > **License Notice** > > This template uses Tencent Hunyuan 3D 2.0 model. Users must: > - Download the model themselves and comply with license terms > - **NOT use in EU, UK, or South Korea** > - Obtain commercial license if >1M monthly active users > - Users are solely responsible for compliance > > See NOTICE and LICENSE for complete terms. HY 3D 2.0 MV Before After HY 3D 2.0 HY 3D 2.0 MV Turbo Before After

• Underdog-Saluki-27B-1.0↗

  ConwayResearch

  Qwen3.8-27B in under 8 GB, tuned to keep tool calling intact. A standard GGUF for stock llama.cpp. Read more: underdog.ai/saluki **Add vision.** Download the vision add-on too, and pass it with `--mmproj`. Then send images through the OpenAI chat API as usual. `--jinja` turns on the Qwen3.8 chat template, which handles tool calls and thinking. The server speaks the OpenAI chat API on port 8080.

• Midm-2.0-Mini-Instruct-Imatrix↗

  cookieshake

• reranker-bert-tiny-gooaq-bce-onnx↗

  cross-encoder-testing

• Qwen-AgentWorld-35B-A3B-AWQ-INT4↗

  cyankiwi

• dolphincoder-starcoder2-7b-GGUF↗

  dagbs

• google.txgemma-2b-predict-GGUF↗

  DevQuasar-11

• THUDM.glm-4-9b-chat-1m-GGUF↗

  DevQuasar-4

• Phi-4-mini-instruct-GGUF↗

  DuoNeural

• Hermes-3-Llama-3.2-3B-imatrix-GGUF↗

  duyntnet