전체 검색

AI 모델 84759

• Qwen-Image-2512-4bit↗

  mlx-community

  MLX-optimized 4-bit quantized version of Qwen-Image-2512 for Apple Silicon. - **Base Model:** Qwen/Qwen-Image-2512 (Dec 31, 2025) - **Quantization:** 4-bit - **Framework:** MLX (Apple Silicon optimized) - **Converted with:** mflux 0.14.0 - 8-bit (34GB) - 6-bit (29GB) - 5-bit (27GB) - 4-bit (24GB) - 3-bit (22GB)

• smart-turn-v3↗

  mlx-community

• ada-coder-qwen2.5-1.5b-GGUF↗

  mradermacher

• Aitana-7B-S-base-1.0-i1-GGUF↗

  mradermacher

• Anime-Speech-Japanese-Refiner-i1-GGUF↗

  mradermacher

• Capybara-Tess-Yi-34B-200K-i1-GGUF↗

  mradermacher

• DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-GGUF↗

  mradermacher

• gemma-3-12b-it-codeforces-SFT-i1-GGUF↗

  mradermacher

• gemma4-tamil-e4b-it-GGUF↗

  mradermacher

• granite-speech-4.1-2b-plus-i1-GGUF↗

  mradermacher