- Meta will have 350,000 of Nvidia's fastest AI GPUs by end of year, buying AMD's MI300, too https://www.tomshardware.com/tech-industry/meta-will-have-350000-of-nvidias-fastest-ai-gpus-by-end-of-year-buying-amds-mi300-too 17 comments amd
Linking pages
- AMD removes Taiwan branding from CPUs, says change wasn't made to appease China | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/amd-removes-taiwan-branding-from-cpus-says-change-wasnt-made-to-appease-china 301 comments
- Using GPT-4 to generate 100 words consumes up to 3 bottles of water — AI data centers also raise power and water bills for nearby residents | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/using-gpt-4-to-generate-100-words-consumes-up-to-3-bottles-of-water-ai-data-centers-also-raise-power-and-water-bills-for-nearby-residents 196 comments
- China planning 1,600-core chips that use an entire wafer — similar to American company Cerebras 'wafer-scale' designs | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/china-planning-1600-core-chips-that-use-an-entire-wafer-similar-to-american-company-cerebras-wafer-scale-design 115 comments
- SSD overclocking yields big performance gains — overclocked SSD controller and NAND may lead to premature degradation or data loss, though | Tom's Hardware https://www.tomshardware.com/pc-components/ssds/ssd-overclocking-yields-big-performance-gains 93 comments
- AMD's customers begin receiving the first Instinct MI300X AI GPUs — the company's toughest competitor to Nvidia's AI dominance is now shipping | Tom's Hardware https://www.tomshardware.com/tech-industry/supercomputers/amds-customers-begin-receiving-the-first-instinct-mi300x-ai-gpus-companys-toughest-competitor-to-nvidias-ai-dominance-is-now-shipping 66 comments
- TSMC tandem builds exotic new memory with radically lower latency and power consumption — MRAM-Based memory can also conduct its own compute operations | Tom's Hardware https://www.tomshardware.com/pc-components/dram/tsmc-tandem-builds-exotic-new-memory-with-radically-lower-latency-and-power-consumption-mram-based-memory-can-also-conduct-its-own-compute-operations 11 comments
- GPD shoves Ryzen 7 8840U into Win Max 2 handheld -- NPU upgrade will improve AI workloads, but not gaming performance | Tom's Hardware https://www.tomshardware.com/video-games/handheld-gaming/gpd-shoves-ryzen-7-8840u-into-win-max-2-handheld-npu-upgrade-will-improve-ai-workloads-but-not-gaming-performance 7 comments
- Samsung reportedly trials second-gen 3nm chip production -- full ramp of SF3 node coming later this year | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/samsung-reportedly-trials-second-gen-3nm-chip-production-full-ramp-of-sf3-node-coming-later-this-year 4 comments
- Meta is using more than 100,000 Nvidia H100 AI GPUs to train Llama-4 — Mark Zuckerberg says that Llama 4 is being trained on a cluster “bigger than anything that I’ve seen” | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/meta-is-using-more-than-100-000-nvidia-h100-ai-gpus-to-train-llama-4-mark-zuckerberg-says-that-llama-4-is-being-trained-on-a-cluster-bigger-than-anything-that-ive-seen 1 comment
Linked pages
- Intel's German fab will be most advanced in the world and make 1.5nm chips, CEO say | Tom's Hardware https://www.tomshardware.com/tech-industry/manufacturing/intels-german-fab-will-be-most-advanced-in-the-world-and-make-15nm-chips-ceo-say 381 comments
- RTX 4070 Ti Super is right on the RTX 4080's tail — new OpenCL and Vulkan benchmarks show less than a 10% margin between them | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/rtx-4070-ti-super-is-right-on-the-rtx-4080s-tail-new-opencl-and-vulkan-benchmarks-show-less-than-a-10-margin-between-them 156 comments
- Nvidia Sold 900 Tons of H100 GPUs Last Quarter, Says Analyst Firm | Tom's Hardware https://www.tomshardware.com/news/nvidia-sold-900-tons-of-h100-gpus-last-quarter 118 comments
- TSMC delays 3nm Arizona fab by a year, cites lack of U.S. subsidies and waning demand | Tom's Hardware https://www.tomshardware.com/tech-industry/tsmc-delays-3nm-arizona-fab-by-a-year-cites-lack-of-us-subsidies-and-waning-demand 35 comments
- Asus confirms the end of the NUC Extreme lineup - NUC 13 Extreme is the last of its kind | Tom's Hardware https://www.tomshardware.com/desktops/mini-pcs/asus-confirms-the-end-of-the-nuc-extreme-lineup-nuc-13-extreme-is-the-last-of-its-kind 23 comments
- TSMC tandem builds exotic new memory with radically lower latency and power consumption — MRAM-Based memory can also conduct its own compute operations | Tom's Hardware https://www.tomshardware.com/pc-components/dram/tsmc-tandem-builds-exotic-new-memory-with-radically-lower-latency-and-power-consumption-mram-based-memory-can-also-conduct-its-own-compute-operations 11 comments
- Samsung reportedly trials second-gen 3nm chip production -- full ramp of SF3 node coming later this year | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/samsung-reportedly-trials-second-gen-3nm-chip-production-full-ramp-of-sf3-node-coming-later-this-year 4 comments
- Microsoft sets 16GB default for RAM for AI PCs – machines will also need 40 TOPS of AI compute: Report | Tom's Hardware https://www.tomshardware.com/software/windows/microsofts-baseline-ram-for-ai-pcs-set-at-16gb 1 comment
- CPU-Z sees its first native release for Windows on ARM64, though it's missing a few x86 features | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/cpu-z-sees-its-first-native-release-for-windows-on-arm64-though-its-missing-a-few-x86-features 0 comments
Related searches:
Search whole site: site:www.tomshardware.com
Search title: Meta will have 350,000 of Nvidia's fastest AI GPUs by end of year, buying AMD's MI300, too | Tom's Hardware
See how to search.