Skip to main content

NVIDIA · Data center · Module

NVIDIA A100 SXM4 40GB

Exact A100 SXM4 40GB reference specifications and AI deployment guidance, separated from FusionPointAI commercial inventory.

Previous generation Reference only
Compare GPU
Neutral technical reference illustration for NVIDIA A100 SXM4 40GB; not a product photograph
Reference illustration; consult the verified specification table for exact hardware identity. This is not a product photograph.

Verified technical specifications

ManufacturerNVIDIA
Exact SKUA100 SXM4 40GB
Product familyNVIDIA A100
ArchitectureAmpere
GenerationAmpere Data Center
Entity typeModule
LifecyclePrevious generation
Launch dateThe manufacturer has not published this information.
VRAM40 GB
Memory technologyHBM2
Memory bandwidth1,555 GB/s
Power400 W
InterfacePCIe Gen4 host interface
Form factorSXM4 · Module
InterconnectNVLink
MIG / partitioningSupported
AI precision supportFP64, FP32, TF32, BF16, FP16, INT8, INT4
Software stackcuda, vllm, sglang, tensorrt-llm

AI workload suitability

LLM inference

Best suited to smaller checkpoints, compressed models or distributed configurations sized by the recommendation engine.

Fine-tuning and training

Designed for sustained accelerator workloads; training suitability depends on interconnect, precision and cluster topology.

Image, video and embeddings

FP16 acceleration supports common generative and vector workloads within the listed VRAM envelope.

Power and cooling

400 W published power requires chassis, airflow and power delivery for this exact form factor.

Multi-GPU use

NVLink is the recorded interconnect path; topology must still be validated at node level.

Software ecosystem

cuda, vllm, sglang, tensorrt-llm

Product timeline

nvidia-a100-40gb @ abb541b542a886c16a50847f29595330d4e3feea5e41bb598e6509be4bd9cd4c

Official source

Official manufacturer source

https://www.nvidia.com/en-us/data-center/a100/

Last verified: 2026-08-24