The Qwen/Qwen2.5-7B-Instruct galaxy

7,552 models are built on Qwen/Qwen2.5-7B-Instruct: 1,735 quantized, 2,493 fine-tuned, 2,924 adapters and 400 merges. Together they were downloaded 13,290,324 times in the last 30 days.

Most downloaded direct derivatives

• Qwen/Qwen2.5-7B-Instruct-AWQ (quantized), 2.9M downloads in 30 days
• unsloth/Qwen2.5-7B-Instruct (finetune), 189.2K downloads in 30 days
• bartowski/Qwen2.5-7B-Instruct-GGUF (quantized), 182.9K downloads in 30 days
• MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF (quantized), 145.7K downloads in 30 days
• Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4 (quantized), 144.3K downloads in 30 days
• Qwen/Qwen2.5-7B-Instruct-GGUF (quantized), 141.9K downloads in 30 days
• unsloth/Qwen2.5-7B-Instruct-bnb-4bit (quantized), 117.9K downloads in 30 days
• unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit (quantized), 89.6K downloads in 30 days
• lmstudio-community/Qwen2.5-7B-Instruct-GGUF (quantized), 19.6K downloads in 30 days
• nvidia/Eagle2.5-8B (merge), 18.4K downloads in 30 days
• langfeng01/GiGPO-Qwen2.5-7B-Instruct-WebShop (finetune), 15.6K downloads in 30 days
• saidutta69/Qwen2.5-7B-Instruct-heretic (quantized), 14.4K downloads in 30 days
• QuantFactory/Qwen2.5-7B-Instruct-Uncensored-GGUF (quantized), 12.8K downloads in 30 days
• paultimothymooney/Qwen2.5-7B-Instruct-Q4_K_M-GGUF (quantized), 12.5K downloads in 30 days
• RedHatAI/Qwen2.5-7B-Instruct-FP8-dynamic (quantized), 11.3K downloads in 30 days
• QuantFactory/Qwen2.5-7B-Instruct-abliterated-v2-GGUF (quantized), 9.8K downloads in 30 days
• Efficient-Large-Model/Fast_dLLM_v2_7B (finetune), 8.6K downloads in 30 days
• PKU-ML/G1-7B (finetune), 7.3K downloads in 30 days
• huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2 (finetune), 7.2K downloads in 30 days
• richardyoung/Qwen2.5-7B-Instruct-abliterated-GGUF (quantized), 5.3K downloads in 30 days
• liuwenhan/reasonrank-7B (finetune), 5K downloads in 30 days
• Orion-zhen/Qwen2.5-7B-Instruct-Uncensored (finetune), 4.1K downloads in 30 days
• mradermacher/Qwen2.5-7B-Instruct-i1-GGUF (quantized), 3.8K downloads in 30 days
• lmstudio-community/Qwen2.5-7B-Instruct-MLX-4bit (quantized), 2.8K downloads in 30 days
• mradermacher/Qwen2.5-7B-Instruct-GGUF (quantized), 2.7K downloads in 30 days