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-VL-2B-Instruct-unsloth-bnb-4bit-Vietnamese-LoRAQwen3-VL-2B-Instruct-unsloth-bnb-4bit-Vietnamese-bill-diagnosis-LoRAtinyllama-coder-py-4bit-v10seallm-v3-4bit-qloralegalbizai-vistral-7b-qlora-4-bitQwen-3-4B-unsloth-4bitLlama-3.2-3B-Instruct-unsloth-bnb-4bit-godot-code4B-bitnet-DUS-bf16Qwen3.6-27B-Opus4.6-Reasoning-MLX-4bitQwen3-4B-Thinking-2507-bnb-4bit-godot-loraemergency-llama32-1b-finetune-rmsys3-mlx-4bitLeoLM-leo-mistral-7b-mixtral-and-gpt4-explanation-3-epochs-qlora-4bitllama-3-8b-Instruct-bnb-4bit-from-scratch-Galilo-V.1.3.0Llama-3.2-1B-Instruct-bnb-4bit-codexllama-3-3b-Instruct-bnb-4bit-Law-de-2autrain-model3-ph-4k-4bitllama-3-3b-Instruct-bnb-4bit-Law-de-1Llama-2-7b-hf-codealpaca-4bitUIGEN-T2-7B-mlx-4Bitbertin-gpt-j-6B-es-finetuned-BOE-summary-LoRA-neftune_noise_alpha-5-4bitunsloth-llama-2-7b-bnb-4bit-conll2003-rank-4llama-3-8b-Instruct-bnb-4bit-Galilo-v.1.0Qwen3-1.7B-4bit-catgirl-LoRALlama-3.2-1B-bnb-4bitQwen3-VL-4B-Thinking-unsloth-bnb-4bit_finetunedLlama-2-70b-chat-4bit-japaneseqwen-bitcoin-chat-manual-Qwen3-4B-Thinking-2507Llama-3.1-8B-bnb-4bitqwen3-4b-bitext-customer-supportQwen3vl-8b-qlora-4bit-Japanese-photo-conversation