Inferbase
Beta
AMD Instinct MI100
Datacenter
The MI100 introduced AMD's CDNA architecture with Matrix Cores for AI acceleration. A capable HPC and ML accelerator with 32GB HBM2 memory at competitive power efficiency.
VRAM
32 GB
Memory
HBM2
Bandwidth
1229 GB/s
TDP
300W
Suitable Workloads
Smaller Language Models
Inference for 7B-13B parameter models
Enterprise Deployment
Designed for 24/7 datacenter operations
Key Highlights
- Built on CDNA 1 architecture
- 480 AI accelerator cores for tensor operations
- 7,680 compute cores for parallel processing
- PCIe form factor
Memory
VRAM32 GB
Memory TypeHBM2
Memory Bandwidth1229 GB/s
Compute Performance
FP32 (Single Precision)11.5 TFLOPS
FP16 (Half Precision)184.6 TFLOPS
BF1692.3 TFLOPS
INT8184.6 TOPS
Architecture
ArchitectureCDNA 1
Compute Cores7,680
AI Accelerators480
Release Year2020
Power & Physical
TDP300 W
Max Power300 W
Form FactorPCIe
PCIe GenerationGen4 x16
Notes
First CDNA architecture GPU. Optimized for HPC and ML workloads.
Models That May Fit on AMD Instinct MI100
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Related Tools
Added Jan 27, 2026
Last updated: Jan 27, 2026
Build Your AI Stack with Confidence
Explore models, compare pricing and benchmarks, and right-size your infrastructure — all in one place.