COMPARE / A40 VS L40S

A40 vs L40S

Specs from the chip makers' datasheets; prices from the live Compute Cafe panel, refreshed hourly. Every rate is an on-demand published price with a source receipt.

CHEAPEST A40
$0.090/hr
SpotGPUs · median $0.65 · 14 providers
CHEAPEST L40S
$0.250/hr
SpotGPUs · median $1.39 · 48 providers
CHEAPER RIGHT NOW
A40
live panel, 2026-09-27
A40L40S
MAKERNVIDIANVIDIA
ARCHITECTUREAmpereAda Lovelace
LAUNCHED20202023
MEMORY48 GB GDDR648 GB GDDR6 ECC
MEMORY BANDWIDTH696 GB/s864 GB/s
TENSOR COMPUTE150 TFLOPS FP16 tensor dense (300 sparse)362 TFLOPS FP16/BF16 tensor dense (733 sparse); 733 TFLOPS FP8 dense
POWER DRAW300 W350 W
INTERCONNECTPCIe 4.0 x16 (NVLink bridge on pairs)PCIe 4.0 x16 (no NVLink)

HOW TO CHOOSE

A40 vs L40S
The L40S has 2.4x the tensor compute and FP8. The A40 only wins when the panel prices it well below - check the spread.
Workload fit
A40: mid-size inference, rendering and vdi. L40S: llm inference up to ~34b, fine-tuning 7b-13b, image and video generation.

A40 VS L40S - FAQ

Which is cheaper to rent, A40 or L40S?
By today's published on-demand rates: A40 starts at $0.090/GPU/hr (median $0.65, 14 providers) and L40S starts at $0.250/GPU/hr (median $1.39, 48 providers). The cheapest live listing is the A40 at SpotGPUs. Figures recompute from the panel on every refresh.
A40 or L40S - which should I rent?
A40: The A40 is Ampere's big-memory visualization card: 48 GB of GDDR6, RT cores, and vGPU support. L40S: The L40S is the workhorse of the inference-and-fine-tuning middle: Ada tensor cores with FP8, 48 GB of memory, and a price well below the H100 line. The side-by-side spec table and live price rows above give the full picture.
Where can I rent A40 and L40S?
14 providers publish A40 rates and 48 publish L40S rates on Compute Cafe. Every row links to the provider's own published price - committed-use and reserved rates are excluded.

Full pricing: A40 · L40S · all comparisons