AI · Article
Nota Optimizes Moonshot AI's Kimi Model, Cutting GPU Purchase Costs by Up to 20%
머니투데이 ·
At a glance
AI optimization company Nota says it shrank Moonshot AI's very large model, Kimi K3.1 Pro, so that it can run on eight cheaper GPUs. The company says this approach can reduce GPU purchase costs by up to 20%.
Key points
- Nota applied pruning, a technique that removes less important parts of a neural network to make the model lighter.
- Nota cut expert modules by up to 37%, which lowered GPU memory use. It kept more than 99% of the original score on a difficult scientific reasoning test.
- The freed-up memory increased the amount of information the model can handle at once, up to 1 million tokens (units that AI uses to process text).
- On cloud platforms, the rental price of B200 GPUs was also found to be up to 22% lower.
Why it matters
Large AI models require expensive hardware, so cost-cutting technology is important for helping more companies use AI.
Original source
노타, 中 문샷AI 모델 최적화…GPU 구매비용 최대 20% 절감 - 머니투데이
머니투데이 · Nov 10, 11:16 KST
Read on 머니투데이 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 머니투데이.
Other coverage
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST