models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFqwen35-9b-harvey-v4-notes-conditioned-100mqwen35-9b-harvey-v4-notes-conditioned-1mqwen35-9b-harvey-v4-notes-conditioned-10mqwen35-9b-harvey-v4-notes-conditioned-30men-indic-translate-26bgemma-3-27b-it-abliterated-Q4_K_M-GGUFgemma-4-12B-it-qat-int4-ovQwen3.5-4B-GGUFqwen35-9b-harvey-v4-notes-conditioned-5mGLM-5.3-FlashQwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUFQwen3.8-27B-mlx-2BitDeepSeek-OCR-2-Q4_K_M-GGUFQwen3.8-27B-Q2_K-GGUFGPC-1trocr-large-printed-e13b_tesseract_MICR_ocr_with_characterQwen3-VL-8B-Instruct-Q8_0-GGUFHuihui-Qwen3.5-4B-abliteratedHarvey-9BQwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bitGemma-4-Harmonia-31B-it-uncensored-heretic-mlx-8BitGemma-4-Harmonia-31B-uncensored-hereticqwen35-9b-harvey-v4-notes-conditioned-100m-kl-0p1NVIDIA-Nemotron-Nano-12B-v2-VL-BF16-Q2_K-GGUFQwen3-VL-2B-Instruct-Q8_0donut-base-sroieqwen35-9b-harvey-v4-notes-conditioned-100m-kl-0p01Harmonic-9BSmolVLM-256M-Instruct-GGUF
