NVIDIA H200 141GBvsNVIDIA B200 180GB
NVIDIA H200 141GB vs NVIDIA B200 180GB: Specs, Benchmarks & Cloud Pricing
Full technical comparison of NVIDIA H200 141GB and NVIDIA B200 180GB — VRAM, memory bandwidth, FP16 TFLOPS, TDP, and live cloud pricing across all providers. Updated July 2026.
Technical Specifications
Spec
NVIDIA H200 141GB
NVIDIA B200 180GB
Architecture
Hopper
Blackwell
VRAM
141 GB HBM3e
180 GB HBM3e
Memory bandwidth
4,800 GB/s
8,000 GB/s
FP16 performance
989 TFLOPS
4,500 TFLOPS
TDP
700 W
1,000 W
NVLink support
Yes
Yes
Release year
2024
2024
Green = better value for that metric.
NVIDIA H200 141GB
The H200 upgrades the H100 with 141GB HBM3e memory and 4.8 TB/s bandwidth — a massive boost for memory-bound workloads like large LLM inference.
Best For
- Very large LLMs
- Memory-bound inference
- Multi-modal models
NVIDIA B200 180GB
The B200 is NVIDIA's Blackwell flagship — 4.5 PFLOPS FP16 and 8 TB/s memory bandwidth make it the most powerful GPU available for AI training at scale.
Best For
- Next-gen LLM training
- Trillion-parameter models
- AI factories