Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
200+ Roleplay, Creative Writing, Uncensored, NSFW models.
Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on.
770
Unsloth Dynamic 2.0 Quants
New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
638
🚀 Qwen-MTP
⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy.
11
DINOv3
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
649
🍎 Qwopus3.6
This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e
55
200+ Roleplay, Creative Writing, Uncensored, NSFW models.
Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on.
770
Unsloth Dynamic 2.0 Quants
New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
638
🚀 Qwen-MTP
⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy.
11
DINOv3
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
649
🍎 Qwopus3.6
This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e
55