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.

Source: BlockBeats

Disclaimer: The current content is sourced from third-party perspectives or directly translated by AI from third-party perspectives. CoinEx does not guarantee the authenticity, accuracy, and originality of the content, and it does not constitute any investment advice from CoinEx. The prices of cryptocurrencies are highly volatile, please be aware of the potential risks.

Related NewsView All

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

Hot

Coins
Price
24H Change