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.
Dolphin-Mistral-24B-Venice-Edition-PatchedQwen2.5-Coder-14B-Instruct-Uncensored-PatchedDolphin3.0-R1-Mistral-24B-PatchedDolphin-2.9.3-Mistral-Nemo-12B-PatchedQwen2.5-Coder-14B-Instruct-Uncensored-PatchedQwen2.5-Coder-32B-Instruct-Uncensored-PatchedGemma-2-9B-Uncensored-PatchedDeepSeek-R1-Distill-Llama-8B-Abliterated-PatchedQwen2.5-Coder-14B-Instruct-Uncensored-PatchedDeepSeek-R1-Distill-Qwen-32B-ablated-PatchedMistral-44B-MoE-Patched-MLX-4bit-G64open-chinese-llama-7b-patchSmolLM2-360M-japanese_patch-11393gemma-4-E2B-it-qat-assistant-4bit-mlx-patchedpatched-coder-34bclip-vit-base-patch32_mbart-large-50Qwen2.5-Coder-1.5Bbart_large_pseudoparadetox_llama3_70b_10shot_patchedApertus-8b-instruct-patchedDeepSeer-R1-Vision-Distill-Qwen-1.5B_google_vit-base-patch16-224Apertus-8B-2509-patchedQwen2.5-Coder-7Bpatched-coder-34b-AWQsiq-vl_siglip2-large-patch16-512_qwen2.5-1.5b-instruct_stage1siq-vl_siglip2-large-patch16-512_qwen2.5-0.5b-instruct_stage1vil-t5-base-clip-vit-base-patch32-mlpPhoGPT-7B5-Instruct-Patchpatched-mix-4x7Bsiq-vl_siglip2-large-patch16-512_qwen2.5-1.5b-instruct_stage2act_patch_qwen3_8b_qwen3_8b