Vitalik Buterin Says DeepSeek v4 Supports Local AI Setup on Ethereum
Поделиться:
Ethereum co-founder Vitalik Buterin tested DeepSeek v4 and reported a 2-bit quantized model requiring about 90 GB VRAM that supports larger local AI workloads on a single high-end machine and integration with the Ethereum network. He measured ~35 tokens/sec on Apple hardware versus ~7 tokens/sec on AMD and linked CROPS AI and Ethereum tools to accelerating local-first AI infrastructure, a protocol update likely to boost crypto adoption and on-chain AI use cases.
Рынки предсказаний
Что в фокусе у трейдеров?
- Vitalik Buterin tested DeepSeek v4 and shared local AI performance results.
- Buterin found that DeepSeek v4 runs faster on Apple hardware than on AMD hardware.
- Buterin linked CROPS AI and Ethereum tools to the growth of local-first AI infrastructure.
Ethereum co-founder Vitalik Buterin says the recently released DeepSeek Version 4 supports his local AI setup on the Ethereum network. In his latest post on X, Buterin highlighted a new 2-bit quantized version that runs about 90 GB VRAM, with the capacity to handle larger workloads on a single high-end machine.
DeepSeek v4 Hardware Compatibility
Following an independent test of the protocol, Buterin noted that the results showed about 35 tokens per second on Apple hardware and about 7 tokens per second on AMD hardware. According to him, this wide performance gap highlights why local AI will pay closer attention to ha…
Read The Full Article Vitalik Buterin Says DeepSeek v4 Supports Local AI Setup on Ethereum On Coin Edition.
Читать больше
Bitmine Files $300M Preferred Stock Offering to Buy More Ethereum
