The Qwen/Qwen1.5-MoE-A2.7B-Chat galaxy

11 models are built on Qwen/Qwen1.5-MoE-A2.7B-Chat: 7 quantized, 1 fine-tuned, 3 adapters and 0 merges. Together they were downloaded 33,309 times in the last 30 days.

Most downloaded direct derivatives

• amd/Qwen1.5-MoE-A2.7B-Chat-w-int8-a-int8-sym (quantized), 723 downloads in 30 days
• tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF (quantized), 460 downloads in 30 days
• 1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF (quantized), 69 downloads in 30 days
• fernandoruiz/Qwen1.5-MoE-A2.7B-Chat-Q4_0-GGUF (quantized), 64 downloads in 30 days
• Gapsar/Qwen1.5-MoE-A2.7B-Chat-Q3_K_M-GGUF (quantized), 28 downloads in 30 days
• Gapsar/Qwen1.5-MoE-A2.7B-Chat-Q3_K_S-GGUF (quantized), 20 downloads in 30 days
• mlc-ai/Qwen1.5-MoE-A2.7B-Chat-q4f16_1-MLC (quantized), 15 downloads in 30 days
• edp1806/Modele_Chef_Kaggle_MOE (adapter), 11 downloads in 30 days
• yudong0504/qwen-moe-watermark (adapter), 11 downloads in 30 days
• zeromodels/qwen1.5-moe-a2.7b-chat (finetune), 9 downloads in 30 days
• yudong0504/qwen-moe-watermark2 (adapter), 8 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.