Skip to content
Updated minutes ago
nvidia

A40

nvidia · ampere · 48 GB GDDR6 · 300W TDP

VRAM

48 GB

BF16 TFLOPS

37.4

Bandwidth

696 GB/s

From

$0.42/hr

Calculate ROI with this GPU →

Spec Sheet

VRAM48 GB GDDR6
Memory Bandwidth696 GB/s
BF16 TFLOPS37.4
FP16 TFLOPS37.4
FP8 TFLOPS37.4
INT8 TOPS74.8
TDP300W
InterconnectPCIE
Max per Node8
PCIe Gen4
CUDA Compute Capability8.6
Tensor CoresYes

Pricing by Provider

ProviderOn-DemandReservedSpotBadge
tensordock$0.59/hr-$0.42/hrCheapest
vast_ai$0.65/hr-$0.44/hr
runpod$0.89/hr-$0.65/hr
lambda$0.79/hr--

Compatible Models (239)

Training Capabilities

Estimated GPU count for full fine-tuning (AdamW, BF16) and QLoRA

Model SizeFull Fine-TuneQLoRA
7B model3 GPUs1 GPU
13B model6 GPUs1 GPU
70B model28 GPUs1 GPU

Energy Efficiency

Estimated tokens/second per Watt for popular models

Mistral 7B
0.32 t/s/WFP8
Qwen 2.5 7B
0.31 t/s/WFP8
Llama 3.1 8B
0.29 t/s/WFP8
Llama 3.1 70B
0.03 t/s/WFP8
Qwen 2.5 72B
0.03 t/s/WFP8

Similar GPUs

GPUVRAMBF16 TFLOPSBW (GB/s)From
RTX A600048 GB38.7768$0.49/hr
A100 40GB SXM40 GB3121555$0.85/hr
A100 40GB PCIe40 GB3121555$0.69/hr
A1664 GB16.8232$0.72/hr
A10G24 GB35600$0.30/hr