What's the price difference between NVIDIA B300 and NVIDIA H200 NVL?

On Runcrate today, NVIDIA B300 starts at $12.99/hr and NVIDIA H200 NVL starts at $4.63/hr; NVIDIA H200 NVL is cheaper by 64%.

Can I deploy NVIDIA B300 or NVIDIA H200 NVL on Runcrate today?

NVIDIA B300 is on demand in 1 region from $12.99/hr, billed by the second on most GPUs. NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA B300 has 288GB HBM3e. NVIDIA H200 NVL has 141GB HBM3e.

B300 or H200 NVL: 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 H200 NVL: 1 GPU, 71 GB spare. Pick the B300: same GPU count, up to 67% more memory bandwidth.

GPU comparison

B300 vs H200 NVL.

The B300 is ahead on memory (288 GB vs 141 GB) and speed (2.7x the FP16 throughput and up to 67% more memory bandwidth). The H200 NVL makes sense when your model fits in 141 GB and its hourly price is lower.

Launch H200 NVL Reserve a cluster

Rent either on Runcrate

B300from $12.99/hr
$0.045 per GB/hr$0.58 per 100 TFLOPS/hr
Launch B300 B300 pricing
H200 NVLCheaperfrom $4.63/hr
$0.033 per GB/hr$0.55 per 100 TFLOPS/hr
Launch H200 NVL H200 NVL pricing

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.

JobB300H200 NVLPick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
B300: 1 GPU, 218 GB spare
H200 NVL: 1 GPU, 71 GB spare
B300. Same GPU count, up to 67% more memory bandwidth.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
B300: 1 GPU, 272 GB spare
H200 NVL: 1 GPU, 125 GB spare
B300. Same GPU count, up to 67% more memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
B300: 1 GPU, 242 GB spare
H200 NVL: 1 GPU, 95 GB spare
B300. Same GPU count, 2.7x the FP16 throughput.
Train on a full node
FP16 tensor throughput per node
B300: 8x, 18,000 TFLOPS, NVLink
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
B300. 2.7x the FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
B300: Varies by card
H200 NVL: 139 TFLOPS per 100 W
Either. Varies by card.

Compare another pair

Blackwell

NVIDIA B300

from$12.99/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

Hopper

NVIDIA H200 NVL

from$4.63/hrCheaper

Available now · 2 regions

Memory: 141 GB HBM3e
FP16 tensor: 835 TFLOPS
Bandwidth: 4.8 TB/s

Launch H200 NVL Reserve a cluster

Full pricing details

At a glance

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

Memory

NVIDIA B300288 GB

NVIDIA H200 NVL141 GB

Memory bandwidth

NVIDIA B300up to 8.0 TB/s

NVIDIA H200 NVL4.8 TB/s

FP16 tensor

NVIDIA B3002250 TFLOPS

NVIDIA H200 NVL835 TFLOPS

Hourly price, from (live)

NVIDIA B300$12.99/hr

NVIDIA H200 NVL$4.63/hr

Full specs

The complete spec sheet.

Spec	NVIDIA B300	NVIDIA H200 NVL
Architecture	Blackwell	Hopper
Memory	288 GB	141 GB
Memory type	HBM3e	HBM3e
Memory bandwidth	up to 8.0 TB/s	4.8 TB/s
FP32	75 TFLOPS	60 TFLOPS
FP16 tensor	2250 TFLOPS	835 TFLOPS
INT8	187.5 TOPS	1670 TOPS
TDP	up to 1400 W	600 W
Form factor	SXM	PCIe
NVLink	Yes	In groups of 4
GPUs per node	8	8
Hourly price (live)	from $12.99/hr	from $4.63/hr

Questions

B300 or H200 NVL. What buyers ask first.

Other comparisons