Tinygrad claims that GLM5.2 can achieve 120 tok/s on a dual-machine interconnected Blackwell configuration, with a price of $150,000.

GPU0%
GLM0%

BlockBeats News, June 21st, GPU retailer Tinygrad announced that, according to reliable sources, the GLM 5.2 model can achieve a inference speed of 120 tokens per second on two networked Blackwell architecture tinyboxes.

The price of this configuration is $150,000, with the option to choose between two standard tinyboxes or one tinybox Pro, both capable of delivering the aforementioned performance. Tinygrad is promoting this as a selling point, emphasizing a private deployment route of "one-time purchase, never pay cloud fees," directly competing with pay-as-you-go cloud inference services.

As of now, this news has not been officially confirmed by the GLM team, and Tinygrad has not disclosed further technical details.

---------------------------------
Click the original text link below to join the BlockBeats · Lark AI News channel, monitoring global AI trends and news 24/7.

منبع：BlockBeats

سلب مسئولیت: منبع محتوای حاضر، نقطه نظرات شخص ثالث است یا مستقیما توسط هوش مصنوعی از نظرات شخص ثالث ترجمه شده است. کوینکس صحت، دقت و اصالت آن را تضمین نمی کند و این محتوا به هیچ وجه توصیه سرمایه گذاری از جانب کوینکس محسوب نمی شود. قیمت رمزارزها بسیار پرنوسان است، لطفا از خطرات احتمالی مطلع باشید.

اخبار مرتبطمشاهده همه

Serenity: SIVE is not just a CPO laser supplier, but a key player in the next-generation optical interconnect architecture

Analysis: The gap between open-source AI and cutting-edge models has shrunk from 12 months to 4 months. By the end of the year, top-tier intelligence may be available for free download.

JPMorgan Chase: AI Capital Spending Raised to $5.5 Trillion, Broadcom Expected to Exceed $150 Billion in AI Revenue by 2027

برترین جستجوها

کوین ها
قیمت
تغییرات ۲۴ ساعته