Skip to main content
AMD Says Ryzen AI Outperforms RTX Spark in CPU Performance, Battery Life and Price - www.thelec.net

AMD Says Ryzen AI Outperforms RTX Spark in CPU Performance, Battery Life and Price - www.thelec.net

NVIDIA GPUs
5 lis 2026, 04:50Hardware News
Oryginał
1 min read

AMD's Ryzen AI CPU delivers 14% better performance than Nvidia's RTX Spark in benchmark tests, with nearly 50% longer battery life during gaming and 17% lower system costs.

AMD highlighted the gaming efficiency of its artificial intelligence PCs compared with rival products and unveiled AI optimization results achieved in collaboration with South Korean companies at the AMD Advancing AI Seoul 2026 event.

Performance Claims

Alexey Navolokin, AMD's senior director of commercial sales for Asia-Pacific, stated that AMD's CPU delivered 14% better performance than Nvidia's RTX Spark in Cinebench 2024 multi-core benchmark tests.

Battery life during gaming was also nearly 50% longer.

Alexey Navolokin, Senior Director of Commercial Sales for APAC at AMD

Navolokin also claimed that AMD systems are about 17% cheaper and noted that RTX Spark does not properly support popular online games due to incompatibility with anti-cheat software.

Technical Specifications

AMD's Ryzen AI Max+ 395, codenamed Strix Halo, features a CPU with up to 16 cores, a Radeon 8060S GPU based on RDNA 3.5 architecture and up to 128GB of LPDDR5X memory. The RTX Spark CPU has 20 cores.

The Radeon 8060S offers performance comparable to Nvidia's laptop RTX 4060 to RTX 4070 GPUs, though AMD did not compare graphics performance directly with RTX Spark.

Korean Optimizations

South Korean companies demonstrated optimizations for Strix Halo. Nota AI used its proprietary agent to optimize AI models, achieving inference performance improvements of up to 30% across several large language models.

Clevi developed Uniform, a Strix Halo-based document processing data engine with a concurrent acceleration pipeline that enabled simultaneous NPU and GPU processing, reducing waiting time before the first response by about 40%.

Z.ai
Article written by AI
Z.ai GLM-4.5-FlashFree
Free AI articles150 of 150
No limit after signing in with Telegram