Skip to content

A100 80GB SXM vs A100 40GB SXM

Side-by-side comparison of the NVIDIA A100 80GB SXM and the NVIDIA A100 40GB SXM for AI inference workloads.

Specifications

SpecA100 80GB SXMA100 40GB SXM
Generationampereampere
Memory TypeHBM2eHBM2e
VRAM80 GB40 GB
Memory Bandwidth2,039 GB/s1,555 GB/s
BF16 TFLOPS312312
FP16 TFLOPS312312
FP8 TFLOPS312312
INT8 TOPS624624
TDP400 W400 W
Interconnectnvlinknvlink
NVLink Bandwidth600 GB/s600 GB/s
Max GPUs per Node88
PCIe GenGen 4Gen 4
CUDA Compute Capability88

Pricing

A100 80GB SXM

ProviderOn-DemandReservedSpot
runpod$2.72/hr-$2.09/hr
lambda$1.99/hr$1.49/hr-
coreweave$2.21/hr$1.62/hr-
aws$3.67/hr$2.39/hr-
gcp$3.67/hr$2.48/hr-
azure$3.67/hr$2.45/hr-
vast ai$1.80/hr-$1.30/hr
tensordock$1.79/hr-$1.29/hr
fluidstack$1.69/hr-$1.19/hr

A100 40GB SXM

ProviderOn-DemandReservedSpot
runpod$1.64/hr-$1.19/hr
lambda$1.29/hr--
aws$3.06/hr$1.96/hr-
gcp$2.93/hr$1.98/hr-
vast ai$1.30/hr-$0.89/hr
tensordock$1.19/hr-$0.85/hr

Cheapest available rate: A100 80GB SXM at $1.19/hr vs A100 40GB SXM at $0.85/hrA100 40GB SXM is +40% cheaper

Efficiency Metrics

TFLOPS / Watt

0.8

A100 80GB SXM

vs

0.8

A100 40GB SXM

BF16

VRAM / Dollar

67.2

A100 80GB SXM

vs

47.1

A100 40GB SXM

GB/$/hr

Bandwidth / Watt

5.1

A100 80GB SXM

vs

3.9

A100 40GB SXM

GB/s/W

Models (FP16, 1 GPU)

182.0

A100 80GB SXM

vs

154.0

A100 40GB SXM

Model Compatibility (FP16, Single GPU)

Only on A100 80GB SXM (28)

  • Yi 1.5 34B
  • Qwen 2.5 32B
  • Qwen 2.5 Coder 32B
  • Aya 23 35B
  • Command R
  • DeepSeek Coder 33B
  • DeepSeek R1 Distill 32B
  • Gemma 2 27B
  • Gemma 3 27B
  • InternLM 2.5 20B
  • InternVL2 26B
  • Vicuna 33B
  • Code Llama 34B
  • Codestral 22B
  • Mistral Small 24B
  • Mistral Small 3.1 24B
  • Qwen 3 32B
  • GigaChat 20B
  • CogVLM2 19B
  • Solar Pro 22B
  • +8 more

Both (154)

  • Yi 1.5 9B
  • Yi Coder 9B
  • GTE Qwen2 7B
  • Marco O1
  • Qwen 1.5 MoE A2.7B
  • Qwen 2 Audio 7B
  • Qwen 2.5 14B
  • Qwen 2.5 3B
  • OLMo 2 13B
  • OLMo 2 7B
  • Amazon Nova Lite
  • OpenELM 3B
  • BGE Large EN v1.5
  • BGE M3
  • Baichuan 2 13B
  • OctoCoder 15B
  • StarCoder2 15B
  • StarCoder2 3B
  • StarCoder2 7B
  • Aya 23 8B
  • +134 more

Only on A100 40GB SXM (0)

None

Summary

The A100 80GB SXM (ampere generation) offers 80GB of HBM2e with 312 BF16 TFLOPS and 2,039 GB/s memory bandwidth at 400W TDP.

The A100 40GB SXM (ampere generation) offers 40GB of HBM2e with 312 BF16 TFLOPS and 1,555 GB/s memory bandwidth at 400W TDP.

The A100 80GB SXM has +100% more VRAM, allowing it to run larger models without multi-GPU setups.

From a cost perspective, the A100 40GB SXM is more affordable at $0.85/hr vs $1.19/hr for the A100 80GB SXM.

More GPU Comparisons