What's the price difference between NVIDIA B300 and NVIDIA L40S?

On Runcrate today, NVIDIA B300 starts at $11.05/hr and NVIDIA L40S starts at $0.54/hr per GPU on a 2-GPU machine; NVIDIA L40S is cheaper by 95%.

Can I deploy NVIDIA B300 or NVIDIA L40S on Runcrate today?

NVIDIA B300 is on demand in 1 region from $11.05/hr, billed by the second on most GPUs. NVIDIA L40S is on demand in 6 regions from $0.54/hr per GPU on a 2-GPU machine, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA B300 has 288GB HBM3e. NVIDIA L40S has 48GB GDDR6.

B300 or L40S: which holds a 70B model in 8-bit weights?

It needs 70 GB of 8-bit weights. On the B300: 1 GPU, 218 GB spare. On the L40S: 2 GPUs (96 GB). Pick the B300: fits on one GPU.

GPU comparison

B300 vs L40S.

The B300 is ahead on memory (288 GB vs 48 GB) and speed (6.2x the FP16 throughput and up to 9.3x the memory bandwidth). The L40S makes sense when your model fits in 48 GB and its hourly price is lower.

Launch L40S Reserve a cluster

Rent either on Runcrate

B300from $11.05/hr
$0.038 per GB/hr$0.49 per 100 TFLOPS/hr
Launch B300
L40SCheaperfrom $0.54/hr per GPU
on a 2-GPU machine
$0.011 per GB/hr$0.15 per 100 TFLOPS/hr
Launch L40S

Live hourly price, then per GB of memory and per 100 FP16 TFLOPS.

Which is better for

Which to pick for each job. Memory fit and throughput, from the datasheets.

JobB300L40SPick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
B300: 1 GPU, 218 GB spare
L40S: 2 GPUs (96 GB)
B300. Fits on one GPU.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
B300: 1 GPU, 272 GB spare
L40S: 1 GPU, 32 GB spare
B300. Same GPU count, up to 9.3x the memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
B300: 1 GPU, 242 GB spare
L40S: 1 GPU, 2 GB spare
B300. Same GPU count, 6.2x the FP16 throughput.
Train on a full node
FP16 tensor throughput per node
B300: 8x, 18,000 TFLOPS, NVLink
L40S: 4x, 1,448 TFLOPS
B300. 8 GPUs per node, not 4.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
B300: Varies by card
L40S: 103 TFLOPS per 100 W
Either. Varies by card.

Compare another pair

Blackwell

NVIDIA B300

from$11.05/hr

Available now · 1 region

Memory: 288 GB HBM3e
FP16 tensor: 2250 TFLOPS
Bandwidth: up to 8.0 TB/s

Launch B300 Reserve a cluster

Full pricing details

Ada Lovelace

NVIDIA L40S

from$0.54/hr per GPUCheaper

on a 2-GPU machine

Available now · 6 regions

Memory: 48 GB GDDR6
FP16 tensor: 362 TFLOPS
Bandwidth: 864 GB/s

Launch L40S Reserve a cluster

Full pricing details

At a glance

Spec by spec. The longer bar is the better number.

Memory

NVIDIA B300288 GB

NVIDIA L40S48 GB

Memory bandwidth

NVIDIA B300up to 8.0 TB/s

NVIDIA L40S864 GB/s

FP16 tensor

NVIDIA B3002250 TFLOPS

NVIDIA L40S362 TFLOPS

Hourly price, from (live)

NVIDIA B300$11.05/hr

NVIDIA L40S$0.54/hr

Full specs

The complete spec sheet.

Spec	NVIDIA B300	NVIDIA L40S
Architecture	Blackwell	Ada Lovelace
Memory	288 GB	48 GB
Memory type	HBM3e	GDDR6
Memory bandwidth	up to 8.0 TB/s	864 GB/s
FP32	75 TFLOPS	91.6 TFLOPS
FP16 tensor	2250 TFLOPS	362 TFLOPS
INT8	187.5 TOPS	733 TOPS
TDP	up to 1400 W	350 W
Form factor	SXM	PCIe
NVLink	Yes	No
GPUs per node	8	4
Hourly price (live)	from $11.05/hr	from $0.54/hr per GPU on a 2-GPU machine

Questions

B300 or L40S. What buyers ask first.

Other comparisons