SixVolts author hub
Swift Qwen3.8 27B GGUF for one Radeon PRO V620 This is a quantization of UkisAI's Swift Qwen3.8 27B https://huggingface.co/ukisai/Swift Qwen3.8 27b that is optimized to work better on older hardware. It fits on one 32 GB GPU with 64k context and your choice of two speculative de…
Models
6
Downloads
2,997
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.