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.
Qwen3-14B-Uncensored-Q4_K_M-GGUFLlama-3.2-1B-Instruct-Uncensored-Q4_K_M-GGUFadtc-agri-sft-qwen3-0.6B-GGUF-Q4_K_MDeepSeek-R1-Distill-Qwen-1.5B-Fully-Uncensored-Q4_K_M-GGUFDeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner-Q4_K_M-GGUFThinkingCap-Qwen3.5-2B-Q4_K_M-GGUFGemini-Q4_0-GGUFphi-3-on-mac-Q4_0-GGUFqwen-medical-7B-Q4_K_M-GGUFMS2501-24b-Ink-ep2-adpt-Q4_K_M-GGUFGemmax-Q4_0-GGUFgemma-270m-ko-en-Q4_0-GGUFUIGEN-T3-14B-Preview-Q4_0-GGUFgemma-4-12B-it-qat-q4_0-unquantized-heretic-loracyber-ai-2025-base02-Q4_K_M-GGUFgemma-4-E2B-Queen-it-qat-q4_0-unquantized-loraACS-Mistral-v0.3-7B-q4-PEACC-Mistral-v0.3-7B-q4-PEspot_m7b_q4_qlora_v0.2_cp50ACS-Mistral-v0.3-7B-q4-AbstRCTARI-Mistral-v0.3-7B-q4-AbstRCTgemma-4-E4B-Queen-it-qat-q4_0-unquantized-loraARI-Mistral-v0.3-7B-q4-PEgpu_q4Bprometheus-0088gpu_q4Bvertex2-self-preservation15-15-0k1e-3-a750gpu_q4Bacc1-self-pres-20-20-0k-1e-3-42c2top_10k_by_final_score_diverse_2048_th0.95_batch32gemma-4-E4B-Queen-it-qat-q4_0-unquantized-loraACC-Mistral-v0.3-7B-q4-AbstRCTq4
