TensorCore.si Blog
Tensor Cores, GPUs and AI chips, explained
In-depth guides, generation-by-generation breakdowns and analysis of the hardware that trains and runs modern AI.
TOPS vs TFLOPS: How to Compare AI Chip Performance Numbers
TOPS and TFLOPS both count trillions of operations per second, but vendors quote them at different precisions, with or without sparsity. How to convert…
RTX 5090 for AI: Which LLMs It Runs, How Fast, and Is It Worth It?
The RTX 5090 has 32 GB of GDDR7 at 1.79 TB/s and fifth-generation Tensor Cores with FP4. Which local LLMs and image models fit,…
NPU vs GPU vs TPU: What Is an NPU and How Is It Different?
An NPU is a small, power-efficient AI accelerator inside phone and laptop chips. How NPUs compare with GPUs and TPUs in design, TOPS, memory…
AMD MI355X vs NVIDIA B200: Specs, MLPerf Results and Which to Choose
AMD Instinct MI355X vs NVIDIA B200: 288 GB vs 180 GB of HBM3e at the same 8 TB/s, about 10% more FP8 and FP4…
NVIDIA Rubin Explained: Vera Rubin NVL72 Specs, HBM4 and Rubin vs Blackwell
NVIDIA Rubin is the GPU after Blackwell: 288 GB of HBM4 at 19.2 TB/s, 35 PFLOPS of dense NVFP4 and NVLink 6, paired with…
NVFP4 Explained: NVIDIA's 4-Bit Format for Blackwell
NVFP4 stores values in FP4 E2M1 with an FP8 scale per 16 values and an FP32 tensor scale. How it works, NVFP4 vs MXFP4,…
GB200 NVL72 Explained: 72 GPUs, One NVLink Domain
GB200 NVL72 puts 72 Blackwell GPUs and 36 Grace CPUs in one liquid-cooled rack with 130 TB/s NVLink and 13.4 TB HBM3e. Specs, what…
B200 vs H100: Blackwell vs Hopper Specs and Speed
B200 vs H100: 2.3x the FP16 and FP8 Tensor Core throughput, FP4 at 9 PFLOPS, 180 GB at 8 TB/s, 1.8 TB/s NVLink and…
H100 vs H200: Same GPU, More Memory (Specs Compared)
H200 uses the same Hopper GPU as H100 with 141 GB of HBM3e at 4.8 TB/s instead of 80 GB at 3.35 TB/s. What…
H100 vs A100: Specs, Speed and Which to Choose
H100 vs A100 compared: 989 vs 312 dense FP16 TFLOPS, FP8, 3.35 vs 2.04 TB/s memory bandwidth, NVLink, power and real-world speedups.