1/ Reasoning agents can think through problems, weigh options, and make informed decisions.
@nvidiaai
-
Modern Agents Toggle Reasoning for Efficient Token Use
By
–
2/ Modern agents can toggle reasoning on and off to efficiently use compute and tokens.
-
How Reasoning AI Agents Are Redefining Decision-Making
By
–
How are reasoning AI agents redefining decision-making?
— NVIDIA AI (@NVIDIAAI) 25 août 2025
🧵A thread pic.twitter.com/5zzGQeXtlYHow are reasoning AI agents redefining decision-making?
A thread -
Think SMART Framework Balances AI Accuracy Latency ROI
By
–
The 𝗧𝗵𝗶𝗻𝗸 𝗦𝗠𝗔𝗥𝗧 framework helps enterprises strike the right balance of accuracy, latency and ROI when deploying AI at AI factory scale. Learn more: https://
nvda.ws/41MTqTc -
Open Models Power 70% of AI Inference Workloads
By
–
𝗧echnology ecosystem and install base Open models power over 70% of AI Inference workloads. NVIDIA supports 1,000+ OSS projects and 450+ open models like Llama, Gemma, and GPT-OSS, and collaborates on frameworks like @GoogleDeepMind JAX, @PyTorch
, @lmsysorg (SGLang), -
Blackwell Delivers 4x Performance and 10x Profit Gains
By
–
𝗥eturn On Investment driven by performance Performance per watt per $ = profit. Moving from Hopper to Blackwell delivers 4× more perf and up to 10× profit within the same power budget.
-
NVIDIA Blackwell GB200 NVL72 Delivers 50× AI Productivity Gains
By
–
𝗔rchitecture and software The NVIDIA Blackwell platform + GB200 NVL72 rack system = up to 50× higher AI factory productivity. Throughput + energy and water efficiency gains + full-stack orchestration = scalable inference.
-
Enterprise AI Infrastructure: Scaling Models and Inference Demands
By
–
𝗦cale and complexity Bigger models = greater inference. From quick queries to million-token reasoning, infra demands during inference are soaring. Enterprises are building new AI factories with partners like @CoreWeave
, @Dell
, @googlecloud and more. -
NVIDIA Inference Platform: Balancing Accuracy, Latency, and Cost
By
–
𝗠ulti-dimensional performance Optimal Inference is a trade-off: accuracy, latency, and cost. Some tasks need ultra-low latency (real-time translation), while others prioritize throughput (multi-million-token queries). The NVIDIA Inference Platform accelerates models
-
Smart Inference Deployment: Scaling AI Across Enterprise Systems
By
–
Deploying AI at scale requires you to 𝗧𝗵𝗶𝗻𝗸 𝗦𝗠𝗔𝗥𝗧 about inference: 𝗦cale and complexity 𝗠ulti-dimensional performance
𝗔rchitecture & software
𝗥OI driven by performance
𝗧echnology ecosystem & install base Let’s break it down