The Qwen/Qwen2.5-32B-Instruct galaxy
2,222 models are built on Qwen/Qwen2.5-32B-Instruct: 1,078 quantized, 480 fine-tuned, 427 adapters and 237 merges. Together they were downloaded 3,175,674 times in the last 30 days.
Most downloaded direct derivatives
- Qwen/Qwen2.5-32B-Instruct-AWQ (quantized), 996.2K downloads in 30 days
- bartowski/Qwen2.5-32B-Instruct-GGUF (quantized), 593.2K downloads in 30 days
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 (quantized), 365.9K downloads in 30 days
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 (quantized), 112.5K downloads in 30 days
- unsloth/Qwen2.5-32B-Instruct-bnb-4bit (quantized), 50.8K downloads in 30 days
- MaziyarPanahi/Qwen2.5-32B-Instruct-GGUF (quantized), 26.3K downloads in 30 days
- Qwen/QwQ-32B-Preview (finetune), 11.5K downloads in 30 days
- Qwen/Qwen2.5-32B-Instruct-GGUF (quantized), 11.5K downloads in 30 days
- OpenGVLab/InternVL2_5-38B (merge), 5.9K downloads in 30 days
- sugoitoolkit/Sugoi-32B-Ultra-GGUF (quantized), 3.6K downloads in 30 days
- zetasepic/Qwen2.5-32B-Instruct-abliterated-v2-GGUF (quantized), 3.4K downloads in 30 days
- EasierAI/Qwen-2.5-32B (quantized), 3K downloads in 30 days
- unsloth/Qwen2.5-32B-Instruct (finetune), 2.7K downloads in 30 days
- lmstudio-community/Qwen2.5-32B-Instruct-GGUF (quantized), 2.7K downloads in 30 days
- ThomasBaruzier/QwQ-32B-Preview-GGUF (quantized), 2.5K downloads in 30 days
- legraphista/Qwen2.5-32B-Instruct-IMat-GGUF (quantized), 2.1K downloads in 30 days
- lmstudio-community/Qwen2.5-32B-Instruct-MLX-4bit (quantized), 1.8K downloads in 30 days
- huihui-ai/Qwen2.5-32B-Instruct-abliterated (finetune), 1.7K downloads in 30 days
- Salesforce/SweRankLLM-Large (finetune), 1.6K downloads in 30 days
- lmstudio-community/Qwen2.5-32B-Instruct-MLX-8bit (quantized), 1.3K downloads in 30 days
- second-state/Qwen2.5-32B-Instruct-GGUF (quantized), 1.3K downloads in 30 days
- mradermacher/Qwen2.5-32B-Instruct-i1-GGUF (quantized), 1.2K downloads in 30 days
- gaianet/Qwen2.5-32B-Instruct-GGUF (quantized), 1.1K downloads in 30 days
- Mungert/OpenCodeReasoning-Nemotron-32B-IOI-GGUF (quantized), 841 downloads in 30 days
- mradermacher/Qwen2.5-32B-Instruct-GGUF (quantized), 819 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.