Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
Kataguru Flagship Series
Official Kataguru Flagship Series: Sceptic 35B MoE and Titan 27B Dense with Vision & MTP. GGUF Dual-Quant, vLLM AWQ, and NVFP4.
SEA-CLIP-Tiny (ACCV 2026)
Weights, ablations and training data for SEA-CLIP-Tiny: a 46M-parameter multilingual text-vision embedding model for Southeast Asian languages.
ThinkingCap Qwen 3.8 Quants
Quantized ThinkingCap-Qwen3.8-27B: NVFP4 and NVFP4A4-AWQ (vLLM), GGUF (llama.cpp), MLX (Apple silicon).
Qwen-Image-2.1 Image-to-Image LoRAs
Collection of QI2.1 I2I Manipulation LoRAs
Swift 27B
Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.
Can It Ford (NSF REU 2026)
NSF SCIPE REU 2026, GeoElements Lab, UT Austin. Can a specific car cross a flooded road? Findings, live demo and data.
Kataguru Flagship Series
Official Kataguru Flagship Series: Sceptic 35B MoE and Titan 27B Dense with Vision & MTP. GGUF Dual-Quant, vLLM AWQ, and NVFP4.
ThinkingCap Qwen 3.8 Quants
Quantized ThinkingCap-Qwen3.8-27B: NVFP4 and NVFP4A4-AWQ (vLLM), GGUF (llama.cpp), MLX (Apple silicon).
Qwen-Image-2.1 Image-to-Image LoRAs
Collection of QI2.1 I2I Manipulation LoRAs
Swift 27B
Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.
SEA-CLIP-Tiny (ACCV 2026)
Weights, ablations and training data for SEA-CLIP-Tiny: a 46M-parameter multilingual text-vision embedding model for Southeast Asian languages.
Can It Ford (NSF REU 2026)
NSF SCIPE REU 2026, GeoElements Lab, UT Austin. Can a specific car cross a flooded road? Findings, live demo and data.