UkisAI PRO

ukisai

·

https://ukisai.com

AI & ML interests

None yet

Recent Activity

updated a model about 17 hours ago

ukisai/Swift-Qwen3.8-27b-int4-AMD

updated a model about 17 hours ago

ukisai/Swift-Qwen3.8-27B-NVFP4

updated a model about 17 hours ago

ukisai/Swift-Qwen3.8-27B-GGUF

View all activity

Organizations

None yet

updated 5 models about 17 hours ago

ukisai/Swift-Qwen3.8-27b-int4-AMD

Image-Text-to-Text • 6B • Updated about 12 hours ago • 921 • 6

ukisai/Swift-Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated about 12 hours ago • 12.4k • 41

ukisai/Swift-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated about 12 hours ago • 176k • 390

ukisai/Swift-Qwen3.8-27b-BF16-AMD

Image-Text-to-Text • 28B • Updated about 12 hours ago • 163 • 1

ukisai/Swift-Qwen3.8-27b

Image-Text-to-Text • 28B • Updated about 12 hours ago • 18.2k • 565

updated a Space 2 days ago

Swift Bonsai 2

Swift Bonsai 2, a 2-bit Qwen-based 27B reasoning model

published a Space 2 days ago

Swift Bonsai 2

Swift Bonsai 2, a 2-bit Qwen-based 27B reasoning model

updated a Space 2 days ago

Swift 27B

Qwen3.8-27B that thinks 58% less with near-equal accuracy

published a Space 2 days ago

Swift 27B

Qwen3.8-27B that thinks 58% less with near-equal accuracy

updated a collection 2 days ago

Swift 27B

Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant. • 6 items • Updated about 16 hours ago • 1