Inferbase
Beta
NVIDIA A100 SXM 80GB
Datacenter
The A100 80GB is the high-memory variant of NVIDIA's Ampere datacenter GPU with 80GB HBM2e. A proven workhorse for AI training and HPC workloads in cloud and enterprise deployments.
VRAM
80 GB
Memory
HBM2e
Bandwidth
2039 GB/s
TDP
400W
Suitable Workloads
Large Language Models
Training and inference for models like GPT-4, Llama 70B+
Distributed Training
Multi-node training with fast interconnects
High-Throughput Inference
Optimized for batched inference workloads
Enterprise Deployment
Designed for 24/7 datacenter operations
Key Highlights
- Built on Ampere architecture
- 432 AI accelerator cores for tensor operations
- 6,912 compute cores for parallel processing
- SXM4 form factor
Memory
VRAM80 GB
Memory TypeHBM2e
Memory Bandwidth2039 GB/s
Compute Performance
FP32 (Single Precision)156 TFLOPS
FP16 (Half Precision)312 TFLOPS
BF16312 TFLOPS
INT8624 TOPS
Architecture
ArchitectureAmpere
Compute Cores6,912
AI Accelerators432
Release Year2020
Power & Physical
TDP400 W
Max Power400 W
Form FactorSXM4
PCIe GenerationGen4
Interconnect
Multi-GPU SupportYes
Interconnect Bandwidth600 GB/s
Pricing
MSRP$15,000
Notes
High-memory variant
Models That May Fit on NVIDIA A100 SXM 80GB
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Related Tools
Added Jan 25, 2026
Last updated: Jan 25, 2026
Build Your AI Stack with Confidence
Explore models, compare pricing and benchmarks, and right-size your infrastructure — all in one place.