- Topic
19k Popularity
11k Popularity
42k Popularity
17k Popularity
40k Popularity
18k Popularity
6k Popularity
3k Popularity
113k Popularity
28k Popularity
- Pin
- 🚨 Gate Alpha Ambassador Recruitment is Now Open!
📣 We’re looking for passionate Web3 creators and community promoters
🚀 Join us as a Gate Alpha Ambassador to help build our brand and promote high-potential early-stage on-chain assets
🎁 Earn up to 100U per task
💰 Top contributors can earn up to 1000U per month
🛠 Flexible collaboration with full support
Apply now 👉 https://www.gate.com/questionnaire/6888
- 🔥 Gate Square #Gate Alpha Third Points Carnival# Trading Sharing Event - 5 Days Left!
Share Alpha trading screenshots with #Gate Alpha Trading Share# to split $100!
🎁 10 lucky users * 10 USDT each
📅 July 4, 4:00 – July 20, 16:00 UTC+8
Gate Alpha 3rd Points Carnival Issue 10 is in full swing!
Trade and post for double the chances to win!
Learn more: https://www.gate.com/campaigns/1522alpha?pid=KOL&ch=5J261cdf
- 🎉 [Gate 30 Million Milestone] Share Your Gate Moment & Win Exclusive Gifts!
Gate has surpassed 30M users worldwide — not just a number, but a journey we've built together.
Remember the thrill of opening your first account, or the Gate merch that’s been part of your daily life?
📸 Join the #MyGateMoment# campaign!
Share your story on Gate Square, and embrace the next 30 million together!
✅ How to Participate:
1️⃣ Post a photo or video with Gate elements
2️⃣ Add #MyGateMoment# and share your story, wishes, or thoughts
3️⃣ Share your post on Twitter (X) — top 10 views will get extra rewards!
👉
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 reported that recently, Lenovo Group announced that based on the Lenovo Wentian WA7780 G3 server, it has successfully implemented the single-machine deployment of the DeepSeek-R1/V3 671B large model for the first time in the industry, carrying 100 concurrent users with less than the industry-recognized 1TGB memory (actually 768GB) for a smooth experience. According to Lenovo's test data, in a standard test environment with 512 TOKENs, the system can support 100 concurrent users to continuously obtain a stable output of 10 TOKENs per second, compressing the first TOKEN response time to within 30 seconds.