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.
tiny_OPTForFeatureExtraction-loraqwen3_06B_lora_mathllama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoningLlama-3.2-3B-TechWriter-Instruct-Unslothgemma-4-31b-it-sft-lora-resumed-lastgemma-4-31b-it-lora-lastmetallama3.2-3b-learnedPathi-Lite-Instruct-1.7B-i1-GGUFzephyr-7b-beta-lorallama31-8b-knapsack-lora-statelessllama-3.1-8b-roleplay-BSNL-ggufHuman-Like-Qwen2.5-1.5B-Instruct-i1-GGUFQwen3.8-27B-Samantha_Uncensored_1.1_LoRALlama-3.2-3B-small_Shiro_roleplay-ggufbosun-v3.1-1.7bbosun-v3.1-0.6bPathi-Lite-Instruct-1.7B-GGUFcheckpoints_latentqa_cls_past_lens_addition_Qwen3-8Bqwen3-4b-xlam-function-calling-60k-loraMiniMax-H3-Prompt-Rewriter-LoRA-OmniAthena-70B-L3-i1-GGUFgc-llm-apertus-70b-instruct-2509Qwen2.5-7B-Bangla-Physics-NCTBsmollm-135m-lora-fineweb-faroeseqwen3.5-9b-rp-lora-v2Qwen3-0.6B-accuracy-recovery-loraQwen2.5-Coder-7B-Vietnamese-LoRAllama3-2-1b-pedagogical-GGUFllama-3.2-1b-mini-agentcheckpoints_latentqa_cls_past_lens_Qwen3-14B