K80 vs M60

Open Advisor →

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

Verdict

K80 has 4 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, M60 delivers 1.1× higher FP16 throughput. At $0.18/hr vs $0.23/hr, K80 is the more cost-efficient choice for inference. K80 supports a broader range of models (486 vs 443 from this catalog), giving more flexibility.

Specifications

K80M60
VRAM12 GB8 GB
VRAM TypeGDDR5GDDR5
Memory Bandwidth0.2 TB/s0.2 TB/s
FP16 Performance9 TFLOPS10 TFLOPS
ManufacturerNVIDIANVIDIA
FP8 SupportNoNo
FP4 SupportNoNo

Price / Performance

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

K80M60
$/hr (cheapest)$0.18✓ best$0.23
$/TFLOP (compute value)$0.0206✓ best$0.0238
$/GB VRAM (memory value)$0.0150✓ best$0.0285

Cloud Pricing

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

K80

ProviderOn-demandSpotRent
Microsoft Azure$0.18/hr$0.10/hr

M60

ProviderOn-demandSpotRent
Microsoft Azure$0.23/hr$0.13/hr

Model Compatibility

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

K80 (486 models)

M60 (443 models)

You might also compare…

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