Lenovo AI server achieves local deployment of DeepSeek full-blooded large model for the first time, with less than 1TB, supporting 100 concurrency.
On March 3, Jinshi Data News, Lenovo Group announced that based on Lenovo Wentian WA7780 G3 server, it has achieved the industry's first single-machine deployment of DeepSeek-R1/V3 671B large model, carrying 100 concurrent users smoothly with less than the industry-recognized 1TGB VRAM (actually 768GB). According to Lenovo's test data, in 512
- 3
- 1