The Qwen/Qwen2-7B-Instruct galaxy

531 models are built on Qwen/Qwen2-7B-Instruct: 128 quantized, 106 fine-tuned, 285 adapters and 12 merges. Together they were downloaded 456,868 times in the last 30 days.

Most downloaded direct derivatives

MaziyarPanahi/Qwen2-7B-Instruct-GGUF (quantized), 153.2K downloads in 30 days
Qwen/Qwen2-7B-Instruct-GGUF (quantized), 4.2K downloads in 30 days
mradermacher/Qwen2-7B-Instruct-i1-GGUF (quantized), 2.8K downloads in 30 days
Qwen/Qwen2-7B-Instruct-AWQ (quantized), 1.8K downloads in 30 days
legraphista/Qwen2-7B-Instruct-IMat-GGUF (quantized), 1.8K downloads in 30 days
bartowski/Qwen2-7B-Instruct-GGUF (quantized), 1.5K downloads in 30 days
mradermacher/Qwen2-7B-Instruct-GGUF (quantized), 1.2K downloads in 30 days
bartowski/Qwen2-7B-Instruct-deccp-GGUF (quantized), 927 downloads in 30 days
Tifa-RP/Tifa-7B-Qwen2-v0.1-GGUF (quantized), 892 downloads in 30 days
AITeamVN/Vi-Qwen2-3B-RAG (finetune), 874 downloads in 30 days
featherless-ai-quants/Qwen-Qwen2-7B-Instruct-GGUF (quantized), 851 downloads in 30 days
neulab/Pangea-7B-hf (finetune), 749 downloads in 30 days
QuantFactory/Qwen2-7B-BD-RP-GGUF (quantized), 661 downloads in 30 days
second-state/Qwen2-7B-Instruct-GGUF (quantized), 653 downloads in 30 days
qwp4w3hyb/Qwen2-7B-Instruct-iMat-GGUF (quantized), 633 downloads in 30 days
QuantFactory/Qwen2-7B-Instruct-GGUF (quantized), 601 downloads in 30 days
AITeamVN/Vi-Qwen2-1.5B-RAG (finetune), 590 downloads in 30 days
nvidia/VideoITG-8B (merge), 543 downloads in 30 days
Qwen/Qwen2-7B-Instruct-GPTQ-Int4 (quantized), 451 downloads in 30 days
gaianet/Qwen2-7B-Instruct-GGUF (quantized), 401 downloads in 30 days
nisten/qwenv2-7b-inst-imatrix-gguf (quantized), 294 downloads in 30 days
neulab/Pangea-7B (finetune), 268 downloads in 30 days
RESMPDEV/Qwen2-Wukong-5B-Instruct-Sliced (finetune), 233 downloads in 30 days
CHE-72-ZLab/Alibaba-Qwen2-7B-Instruct-GGUF (quantized), 212 downloads in 30 days
Qwen/Qwen2-7B-Instruct-GPTQ-Int8 (quantized), 209 downloads in 30 days