Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
MOSS-Audio
An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex
62
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with Model Optimizer.
166
Gemma 4
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
199
NVIDIA Nemotron v3
Open, Production-ready Enterprise Models
304
🚀 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.
17
🍎 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
62
Luciole LLM
Open Source LLM in French, English, German, Spanish, Italian, Portuguese, Dutch and Arabic
7
MOSS-Audio
An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex
62
NVIDIA Nemotron v3
Open, Production-ready Enterprise Models
304
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with Model Optimizer.
166
🚀 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.
17
🍎 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
62
Gemma 4
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
199
Luciole LLM
Open Source LLM in French, English, German, Spanish, Italian, Portuguese, Dutch and Arabic
7