Hopper GPU with large 80GB HBM. 2K TFLOPS FP16 for high-performance compute. 125K tok/s MLPerf. Available from 12 providers starting at $1.49/hr.
Metrics
Memory GB80
High-bandwidth memory capacity
TFLOPS FP161,979
FP16 compute performance
ArchitectureHopper
Neural network architecture type
TDP700W
Thermal design power consumption
Min Cloud Price$1.49/hr
Lowest available cloud rental price
Avg Cloud Price$3.50/hr
Average price across providers
Provider Count12
Number of cloud providers offering this GPU
Price UpdatedDec 28, 2025
Last pricing data refresh date
Score Breakdown
training
15%58
LLM training time-to-convergence
ecosystem
15%96
Software stack maturity and framework support
inference
25%70
LLM inference throughput per GPU
performance
30%95
Raw compute throughput and memory bandwidth
availability
15%85
Market supply and cloud instance availability
Compatibility(3)
Sources(1)
Developed by
NVIDIARelated Signals(5)
MI300X Leads MLPerf Inference v5.1 for LLM Throughput
AcceleratorsJan 10
94AMD MI300X achieves highest per-GPU LLM inference throughput in MLPerf Inference v5.1, delivering 21,150 tokens/s per GPU on llama2-70b, outperforming NVIDIA H100 (15,610 tok/s), B200 (13,015 tok/s), and H200 (10,917 tok/s). Industry-standard benchmark validates AMD's competitiveness in AI inference.
Related:
Frontier AI Capabilities Reach Consumer GPUs Within 12 Months
ModelsDec 31
89The best open models runnable on consumer GPUs lag frontier AI by only ~1 year across GPQA, MMLU, and LMArena benchmarks, suggesting rapid capability democratization and regulatory implications.
Related:
NVIDIA AI Compute Stock Doubling Every 10 Months
AcceleratorsDec 31
91Installed AI compute from NVIDIA chips has more than doubled annually since 2020, with new flagship chips accounting for most compute within 3 years of release.
Related:
AWS Announces P5 Instances with H200 GPUs
CloudDec 18
91AWS has launched P5 instances featuring NVIDIA H200 GPUs, now generally available in US East and West regions with EU availability expected in Q1 2026.
Related:
PyTorch Reaches 100M Weekly Downloads
FrameworksDec 15
89PyTorch has surpassed 100 million weekly downloads on PyPI, cementing its position as the dominant deep learning framework for research and production deployments.
Related: