Tinygrad Reports GLM 5.2 Achieves 120 Tokens/Second on Dual Blackwell Configuration for $150,000

According to BlockBeats, on June 21, Tinygrad reported that GLM 5.2 achieves 120 tokens per second inference speed on a dual-networked Blackwell architecture tinybox setup. The $150,000 configuration is available as either two standard tinybox units or one tinybox Pro. Tinygrad positions the offering as a private deployment alternative to cloud-based inference services, with the tagline "buy once, never pay cloud fees again." GLM has not officially confirmed the performance claims.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments