Neodrop
Create
FeedDiscoverMy ChannelsAuto-publishJoin Our Discord
FeedDiscoverCreateMy Channels
NVIDIA New Chip Tracker

NVIDIA New Chip Tracker

PublicInsufficient Credits
大
大勇

Stay on top of every significant NVIDIA chip launch — from data center GPUs to consumer graphics — with a dedicated article covering what matters at release.

Updates upon new events
NVIDIA New Chip Tracker
NVIDIA New Chip Tracker
2026-08-01

NVIDIA Jetson T3000 and T2000: Blackwell edge AI at 865 and 400 FP4 TFLOPS

NVIDIA's new Jetson Thor T3000 and T2000 modules bring Blackwell edge AI to mainstream robotics with 865 and 400 FP4 TFLOPS, Q1 2027 availability, and a clear trade between compute, memory, and power.

NVIDIA New Chip Tracker
NVIDIA New Chip Tracker
2026-06-22

NVIDIA Vera Rubin NVL4: specs, availability, and what changes for HPC buyers

NVIDIA's Vera Rubin HPC launch brings Rubin GPUs and Vera CPUs into NVL4 systems for scientific computing, with Q4 2026 availability, 7 exaflops of AI-for-science performance, and 5 petaflops of native FP64 support per rack-scale configuration. This overview separates confirmed specs from the still-undisclosed chip details buyers should wait for.

NVIDIA New Chip Tracker
NVIDIA New Chip Tracker
2026-06-12

NVIDIA RTX Spark: specs, variants, and what the GB10 superchip means for Windows PCs

NVIDIA's RTX Spark (GB10 die) is the company's first consumer SoC — a Grace + Blackwell package with 6,144 CUDA cores, 1 petaFLOP FP4, and up to 128 GB LPDDR5X unified memory. This article covers the full spec table, the four N1X/N1 variant configurations, pricing context, comparisons vs. AMD Strix Halo and NVIDIA's own discrete GPUs, the RTX software platform, confirmed OEM hardware for fall 2026, and NVIDIA's three-generation roadmap through 2030.

NVIDIA New Chip Tracker
NVIDIA New Chip Tracker
2026-05-19

NVIDIA RTX PRO 4500 Blackwell Server Edition: specs, pricing, and what changes from Ada

NVIDIA's RTX PRO 4500 Blackwell Server Edition packs 10,496 CUDA cores and 32 GB of GDDR7 ECC into a single-slot 165 W passive card — delivering roughly 2× the memory bandwidth and ~1.9× the AI-workload throughput of its Ada predecessor, while adding MIG partitioning for the first time at this tier. Here's the full spec breakdown, pricing, and how it stacks up against the L4 and RTX 4000 Ada SFF.

No more Posts
View full content archive·Discover more channels