00:00
2026-08-25
mindstudio.ai
artificial-intelligence
Run Qwen3.8-27B-Escha-W2 on a 24GB GPU with SGLang
Escha Labs released Qwen3.8-27B-Escha-W2, a 2-bit quantized build of Qwen3.8-27B that fits 10.15 GB of weights on a 24 GB consumer GPU, enabling 64k context out of the box and up to 128k with tuning vā¦