All AI inference chips

MI355X vs B200

Spec-sheet and pricing comparison of AMD Instinct MI355X and NVIDIA B200 with links to continuously measured LLM inference benchmarks on identical workloads.

Spec-sheet comparison

MI355XB200MI355X / B200
Memory per chip288 GB HBM3e180 GB HBM3e1.6x
Memory bandwidth8 TB/s8 TB/s1.0x
Dense FP8 compute5,033 TFLOP/s4,500 TFLOP/s1.12x
Dense FP4 compute10,066 TFLOP/s9,000 TFLOP/s1.12x
TDP1,400 W1,000 W1.4x
Hourly rate (neocloud tier)$2.09/hr$2.07/hr1.01x
Scale-up world size8 chips8 chips1.0x

Ratios are spec-sheet values; see the live compare pages for measured deltas.

Frequently asked questions

Which has more memory, MI355X or B200?
MI355X offers 288 GB HBM3e per chip versus 180 GB HBM3e on B200 (1.6x the capacity).
How do MI355X and B200 prices compare?
At the neocloud tier the SemiAnalysis TCO model rates MI355X at $2.09/hr versus $2.07/hr for B200. Hourly price alone is misleading; the per-dollar compare pages divide measured throughput by these rates.
Is MI355X faster than B200 for LLM inference?
On paper MI355X has 1.12x the dense FP8 compute of B200, but delivered tokens per second depend on the model, framework, precision and interactivity target. InferenceX measures both chips daily on identical workloads; see the live compare pages for current results.

See live benchmark results

Every number above is static hardware data. Delivered tokens per second, cost per million tokens and energy per token are measured continuously on the dashboard:

Go deeper with the SemiAnalysis models

InferenceX measures delivered inference performance. The SemiAnalysis institutional models cover the market behind these chips: who ships them, who buys them, and what they cost to own.