7张图揭示DeFi现状:Fluid领跑DEX大战,USDe改写稳定币格局

marsbit2025-08-07 tarihinde yayınlandı2025-08-08 tarihinde güncellendi

2025年至今对DeFi来说是非常友好的一年。

我们的监管环境已从Gary Gensler领导SEC采取敌对立场,转变为如今对加密友好的局面。而从几乎所有指标来看,DeFi的采用率都在不断增加。

所以我想现在是时候仔细研究DeFi现状相关的7张图表了。

去中心化交易所到中心化交易所交易额正屡创新高

DeFi

来源: The Block

尽管进程缓慢但趋势明显,去中心化交易所正不断蚕食中心化交易所的市场份额。

2022年6月,永续DEX在衍生品领域的市场份额仅为0.98%。三年后,这个数据已增长了11倍。


Fluid是增长最快的DEX

DeFi

来源:DeFiLlama

据报道,Fluid上线不到一年时间,日交易量便一度超越以太坊上的龙头DEX Uniswap。

Fluid DEX V2即将上线,如果Fluid最终在以太坊上赢得DEX之战,我一点也不会感到意外。

在资本效率方面,V2预计将远高于V1版本。


生息型稳定币首次登顶资金流入榜

DeFi

来源: Artemis

近日,Ethena旗下的稳定币USDe首次在两周净流入量上超越了USDT和USDC两大主流稳定币。

为什么这个变化如此重要?

USDT和USDC在稳定币领域长期领跑市场,而如今加密原生解决方案正不断涌现,挑战其主导地位。

我的预测是Resolv、Ethena和Falcon Finance在未来几个月将继续呈指数级增长。


现货以太坊ETF表现良好,但涨势正在放缓

DeFi

来源:Coinglass

经过数周持续刷新单日流入资金历史新高后,以太坊现货ETF近日录得有记录以来最大单日资金流出。

原因可能是,一些传统金融巨头已经获利了结。

不过,如果我们从宏观来看,过去两个月是现货以太坊ETF迄今为止表现最好的阶段。


DeFi正在逼近AI的心智份额

DeFi

来源:Kaito

一年多以来,AI一直在心智占有率上占据领先地位。

但这种局面正在改变,在过去的几个月里,DeFi的关注度增长了两倍多。与此同时,Meme币的关注度大幅减少。

基本面再次变得重要起来。


2025年具有代币回购计划的项目表现最为出色

DeFi

来源:Dexu AI

这标志着市场开始青睐基本面扎实的代币。进行代币回购的协议子类别包括 Hyperliquid、PumpFun、Maple、EtherFi、Kaito、AAVE等项目。


交易所BTC储备量持续下降

DeFi

来源:Crypto Quant

2024年2月以来(正值美国首批比特币现货ETF推出后不久),交易所BTC储备量就持续减少,而这种情况与之前的牛市恰恰相反​​。

本周期内,比特币ETF的资金流入以及加密资产储备公司产生的购买需求,对BTC价格产生了巨大的积极影响。

综上所述,以上就是本期要呈现的全部数据图表。

İlgili Okumalar

Wang Chuan: When the neighbor Lao Wang earned thirty times from investing in memory storage stocks, how can you still avoid anxiety (6) - The trap of homogeneous products

The article, "Wang Chuan: How to Remain Unanxious After Neighbor Lao Wang's Thirty-Fold Gain on Storage Stocks (Part 6) - The Trap of Commoditized Goods," analyzes the cyclical and perilous nature of the data storage industry through historical and current case studies. It begins with the example of Iomega, whose Zip drives led to a stock surge of over 160x in the mid-1990s before collapsing over 97% from its peak due to competition from cheaper CD-R technology. This pattern is characteristic of storage, where products like DRAM are highly commoditized, leading to extreme price volatility. The sector has seen prices crash over 80% multiple times, with companies often facing bankruptcy. The core dynamic is "elastic demand facing heavy-asset, long-cycle, rigid supply." High prices attract new capacity, but the long lead time means supply eventually overshoots, causing sharp price corrections. The current AI-driven boom, exemplified by surging demand for High-Bandwidth Memory (HBM), has led to skyrocketing prices and profit margins for companies like SanDisk and Micron, despite relatively flat production volumes. However, the author warns this high-margin environment is self-defeating. The high profits are already triggering massive new capacity investments (hundreds of billions starting 2026), with supply expected to ramp up by late 2027. When supply catches up, total revenue and profits may fall even as more units are sold. Long-term supply agreements offer little protection, as buyers can find ways to renegotiate if market prices drop, similar to fragile political treaties. Key risks include economic downturns, cuts in AI spending, faster-than-expected capacity expansion (especially from Chinese firms), and innovations in chip/algorithm design that reduce memory needs. A critical trap is that at the cycle's peak, storage stocks often appear cheap with low P/E ratios, luring value investors just before an impending downturn where profits evaporate. The conclusion cautions that for commoditized goods like storage, high margins inevitably destroy themselves, and the current asymmetry favors downside risk over further upside. The neighbor's dream of easy wealth from storage stocks is portrayed as a precarious illusion.

链捕手4 dk önce

Wang Chuan: When the neighbor Lao Wang earned thirty times from investing in memory storage stocks, how can you still avoid anxiety (6) - The trap of homogeneous products

链捕手4 dk önce

AI PCs Are Here, Going Toe-to-Toe with 120B Models Locally! NVIDIA Redefines the "Personal AI Computer" Foundation with RTX Spark

NVIDIA has redefined the "AI PC" standard with the launch of the RTX Spark super chip at GTC 2026. Boasting 1 petaflop (1000 TOPS) of AI performance, it dwarfs the 45-50 TOPS NPUs in current AI PCs. The SoC features a Blackwell GPU, a 20-core Arm CPU co-designed with MediaTek, and crucially, up to 128GB of unified memory shared between CPU and GPU. This architectural shift enables local execution of 120-billion-parameter large language models with million-token context windows, a massive leap from the 9B-40B models typical on current consumer hardware. Beyond AI, use cases include 12K video editing and high-fps ray-traced gaming. Key to enterprise adoption is a security collaboration with Microsoft. Windows security is upgraded, and NVIDIA's OpenShell sandbox runtime is integrated to safely contain AI agent actions. Major software support comes from Adobe, which announced a deep,底层-level rewrite of Photoshop and Premiere to leverage the unified memory for up to 2x performance gains. Six OEMs, including Dell, HP, Lenovo, and Microsoft Surface, will release RTX Spark-based轻薄本 and compact desktops this fall. However, questions remain about real-world performance,功耗, thermal management in laptops, pricing, and the actual impact of the OpenShell sandbox. The RTX Spark represents a fundamental power shift in the PC industry, moving from an x86 CPU-centric model to a GPU-centric SoC platform, but its ultimate success hinges on the upcoming product rollouts and ecosystem validation.

marsbit18 dk önce

AI PCs Are Here, Going Toe-to-Toe with 120B Models Locally! NVIDIA Redefines the "Personal AI Computer" Foundation with RTX Spark

marsbit18 dk önce

Jensen Huang: Vera Rubin Full Mass Production, AI Agent a Key Focus, Challenging Intel to Target the Next-Generation AI PC Gateway

NVIDIA CEO Jensen Huang delivered the keynote speech at GTC Taipei 2026, announcing several major product launches and strategic directions. The company's Vera Rubin architecture is now in full-scale production, with OpenAI, Anthropic, and SpaceX among the first customers. NVIDIA highlighted AI Agent as a key future focus, introducing the Vera CPU designed for AI agents and the Vera BlueField-4 STX for secure, chip-level AI storage processing. A significant move involves challenging Intel in the PC market. NVIDIA, in collaboration with MediaTek, is developing the RTX SPARK PC chip (manufactured by TSMC) for Windows systems, set to launch this fall for laptops and desktops. This signals NVIDIA's push into the next-generation AI PC arena, aiming to provide a vertically integrated core computing platform for the entire Windows ecosystem, similar to Apple's approach. Other announcements include the new Nemotron 3 Ultra AI model and the NVIDIA DSX platform, described as a complete "playbook" for building AI factories, allowing performance simulation and validation before physical deployment. In automotive, the DRIVE Hyperion platform was positioned as a global robotaxi platform, with major Chinese automakers like BYD, Geely, Zeekr, Xiaomi, and Pony.ai already adopting or developing autonomous driving solutions based on it. The Alpamayo 2 super open inference model for robotaxis was also introduced. For robotics, NVIDIA unveiled the Isaac GR00T humanoid robot reference platform for academic research and a large open-source agent tools and skills suite for Physical AI. The company plans to collaborate with global humanoid robot manufacturers, including China's Unitree, whose H2 Plus robot served as the reference hardware for the GR00T platform demonstration.

marsbit45 dk önce

Jensen Huang: Vera Rubin Full Mass Production, AI Agent a Key Focus, Challenging Intel to Target the Next-Generation AI PC Gateway

marsbit45 dk önce

Running MoE on Mobile Phones? Meta Proposes MobileMoE, Speeding Up iPhone 16 Pro by 3.8x

Meta's MobileMoE, a mobile-optimized Mixture-of-Experts (MoE) language model architecture, enables efficient on-device large language model (LLM) inference for the first time on commercial smartphones. Designed for decoder-only Transformers, it replaces dense feed-forward layers with MoE layers. Key design choices include 8 experts with granularity g=8, top-4 routing, and a shared expert. The model undergoes a four-stage training process: pre-training, intermediate training, supervised fine-tuning, and quantization-aware training. Results show MobileMoE models, with similar memory footprint, achieve equal or higher average accuracy across 14 foundational benchmarks while using only 1/2 to 1/4 of the FLOPs compared to dense baselines. After INT4 quantization, they remain competitive. Notably, on an iPhone 16 Pro, MobileMoE-S demonstrates significant speedups: up to 3.8x faster in the prompt phase and 2.2-3.4x faster in per-token generation compared to a dense counterpart, with lower peak memory usage. While MobileMoE establishes a new Pareto frontier for on-device LLMs in accuracy-compute trade-offs, particularly excelling in code and math tasks, it currently lags behind models like Qwen3.5 2B in advanced instruction following and knowledge reasoning. Future work includes improving post-training techniques, exploring NPU deployment, and managing the runtime memory sensitivity of MoE models to varying inputs.

marsbit50 dk önce

Running MoE on Mobile Phones? Meta Proposes MobileMoE, Speeding Up iPhone 16 Pro by 3.8x

marsbit50 dk önce

İşlemler

Spot
Futures
活动图片