A100 80GB PCIe vs DGX Spark (GB10)

Open Advisor →

Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.

Verdict

DGX Spark (GB10) has 48 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, A100 80GB PCIe delivers 2.5× higher FP16 throughput. DGX Spark (GB10) supports a broader range of models (649 vs 636 from this catalog), giving more flexibility.

Specifications

A100 80GB PCIeDGX Spark (GB10)
VRAM80 GB128 GB
VRAM TypeHBM2eLPDDR5X
Memory Bandwidth1.9 TB/s0.3 TB/s
FP16 Performance312 TFLOPS125 TFLOPS
ManufacturerNVIDIANVIDIA
FP8 SupportNoYes
FP4 SupportNoYes

Price / Performance

Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.

A100 80GB PCIeDGX Spark (GB10)
$/hr (cheapest)$1.39
$/TFLOP (compute value)$0.0045
$/GB VRAM (memory value)$0.0174

Cloud Pricing

Cheapest on-demand price per provider (single GPU).

A100 80GB PCIe

ProviderOn-demandSpotRent
RunPod$1.39/hr$0.82/hrRent
Google Cloud$1.85/hr$1.47/hr
Microsoft Azure$3.67/hr$0.40/hr

DGX Spark (GB10)

No cloud pricing available.

Model Compatibility

Models from the catalog that fit on each GPU, grouped by required precision.

A100 80GB PCIe (636 models)

DGX Spark (GB10) (649 models)

You might also compare…

Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons