The Qwen/Qwen2.5-32B galaxy
3,994 models are built on Qwen/Qwen2.5-32B: 2,109 quantized, 1,002 fine-tuned, 573 adapters and 310 merges. Together they were downloaded 7,497,980 times in the last 30 days.
Most downloaded direct derivatives
- Qwen/Qwen2.5-32B-Instruct (finetune), 1.9M downloads in 30 days
- Qwen/QwQ-32B (finetune), 56.3K downloads in 30 days
- baichuan-inc/Baichuan-M2-32B-Q4_K_M-GGUF (quantized), 6.2K downloads in 30 days
- mradermacher/Qwen2.5-32B-i1-GGUF (quantized), 6.2K downloads in 30 days
- mradermacher/Qwen2.5-32B-GGUF (quantized), 3.8K downloads in 30 days
- ThomasBaruzier/Qwen2.5-32B-Instruct-GGUF (quantized), 3.5K downloads in 30 days
- arcee-ai/Virtuoso-Medium-v2-GGUF (quantized), 2.9K downloads in 30 days
- Mungert/QwQ-32B-GGUF (quantized), 2.1K downloads in 30 days
- mlx-community/Qwen2.5-32B-Instruct-4bit (finetune), 1.9K downloads in 30 days
- Mungert/OpenMath-Nemotron-32B-GGUF (quantized), 1.9K downloads in 30 days
- Qwen/Qwen2.5-Coder-32B (finetune), 1.8K downloads in 30 days
- baichuan-inc/Baichuan-M2-32B (finetune), 1.3K downloads in 30 days
- Mungert/LongWriter-Zero-32B-GGUF (quantized), 1.1K downloads in 30 days
- featherless-ai-quants/Qwen-Qwen2.5-32B-GGUF (quantized), 837 downloads in 30 days
- nvidia/OpenReasoning-Nemotron-32B (finetune), 700 downloads in 30 days
- deepcogito/cogito-v1-preview-qwen-32B (finetune), 660 downloads in 30 days
- unsloth/Qwen2.5-32B-bnb-4bit (quantized), 539 downloads in 30 days
- nvidia/OpenMath-Nemotron-32B (finetune), 455 downloads in 30 days
- Verdugie/Opus-Candid-32B-V1 (quantized), 383 downloads in 30 days
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 (finetune), 372 downloads in 30 days
- interpretable-finetuning/qwen2.5-32b-unaliased (finetune), 362 downloads in 30 days
- MiniMaxAI/SynLogic-32B (finetune), 342 downloads in 30 days
- baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 (quantized), 312 downloads in 30 days
- DevQuasar/Qwen.Qwen2.5-32B-GGUF (quantized), 274 downloads in 30 days
- MiniMaxAI/SynLogic-Mix-3-32B (finetune), 259 downloads in 30 days