Collections

Discover the best community collections!

Collections trending this week
AI Orchestration — Agents, Workflows, Routing & Infra
Curated resources on AI orchestration — the coordination layer connecting agents, models, tools, routing and intelligent workflows.
Swift 27B
Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.
Qwen-Image-2.1 Image-to-Image LoRAs
Collection of QI2.1 I2I Manipulation LoRAs
Swift1.5 Flash Next
Swift Flash Next: the next Swift generation. Weights and quantized builds are added here as they are released.
Swift 1.5 27B
Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant.
AI Orchestration — Agents, Workflows, Routing & Infra
Curated resources on AI orchestration — the coordination layer connecting agents, models, tools, routing and intelligent workflows.
Qwen-Image-2.1 Image-to-Image LoRAs
Collection of QI2.1 I2I Manipulation LoRAs
Swift1.5 Flash Next
Swift Flash Next: the next Swift generation. Weights and quantized builds are added here as they are released.
Swift 27B
Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.
Swift 1.5 27B
Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant.