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.
Llama-3.2-1B-Instruct-QLORA_INT4_EO8Llama-3.2-3B-Instruct-QLORA_INT4_EO8dksplit-qwen-loraMeta-Llama-3.1-8B-ft-LoRA-elgrancorpus-it-gguf-q4_k_mLlama-3.2-1B-Instruct-QLORA_INT4_EO8-ETQwen3-14B-RLCD-Decision-LoRAsteam-ai-mention-qwen3-8b-loraSherlock-4B-QLoRALlama-3.2-1B-Instruct-QLORA_INT4_EO8Llama-3.2-1B-Indonesian-QLoraQwen3.8-27B-switchboard-lora-v2qwen3-1.7b-spanish-lora-no-injectqwen3-8b-htr-vines-loraqwen3-1.7b-spanish-lora-with-injectLaw-Guardian-Llama-8B-V2-LoRa-Q8_0-GGUFheller-gpt-qwen14b-loraoppy-qwen3-loraregllm-qwen25-7b-banking-loraqwen25-adv-loraLlama3.2-lora-1B_exl2_q8Llama-3.2-1B-QA-SQAD-QLORAv1MaternaCare-ES-gemma4-qloraMaternaCare-ES-medgemma-qloraLlama-3.2-3B-qloraHAL_9000-Qwen2-0.5B-Instruct_Spanish_English_lora_modelQwen2_0.5B_Spanish_English_raspberry_pi-lora_modelQwen2-7B-Instruct_CODE_Python_Spanish_English_lora_modelQwen2-7B-v2-Instruct_CODE_Python_Spanish_English_lora_modelTinytron-Qwen-0.5B-Depth-Base-Instruct_CODE_Python_Spanish_English_lora_modelHAL_9000-QWEN2-0.5_Spanish_English_lora_model