Mia
@MiaAI_lab
Building with AI & LLMs | Insights, recipes, tools & honest experiments
๊ฐ์
July 2022
364 ํ๋ก์ ์ค 12.2K ํฌ
You can now run GLM-5.2 on 3x @NVIDIAAI DGX Sparks at home ๐คฏ
โข 248k context
โข 15-20 tok/s (content-dependent)
โข MTP for max context / DSpark optional
โข NVFP4+AQLM hybrid
Still a work in progress โ will keep improving over time.
โ
๋ ๋ณด๊ธฐ
