Can I deploy NVIDIA B300 or AMD MI300X on Runcrate today?

NVIDIA B300 is on demand in 1 region from $12.99/hr, billed by the second on most GPUs. AMD MI300X is not in stock on Runcrate right now; reserve a cluster, and once we've verified your company and your need we take your exact spec to GPU owners that fit.

How much VRAM does each GPU have?

NVIDIA B300 has 288GB HBM3e. AMD MI300X has 192GB HBM3.

B300 or MI300X: 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 MI300X: 1 GPU, 122 GB spare. Pick the B300: same GPU count, up to 51% more memory bandwidth.

GPU comparison

B300 vs MI300X.

The B300 is ahead on memory (288 GB vs 192 GB) and speed (72% more FP16 throughput and up to 51% more memory bandwidth). The MI300X makes sense when your model fits in 192 GB and its hourly price is lower.

Launch B300 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
MI300XNot in stock right now
Reserve a cluster MI300X 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.

JobB300MI300XPick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
B300: 1 GPU, 218 GB spare
MI300X: 1 GPU, 122 GB spare
B300. Same GPU count, up to 51% more memory bandwidth.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
B300: 1 GPU, 272 GB spare
MI300X: 1 GPU, 176 GB spare
B300. Same GPU count, up to 51% more memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
B300: 1 GPU, 242 GB spare
MI300X: 1 GPU, 146 GB spare
B300. Same GPU count, 72% more FP16 throughput.
Train on a full node
FP16 tensor throughput per node
B300: 8x, 18,000 TFLOPS, NVLink
MI300X: 8x, 10,459 TFLOPS
B300. 72% more FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
B300: Varies by card
MI300X: 174 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

CDNA 3

AMD MI300X

Not in stock right now

Memory: 192 GB HBM3
FP16 tensor: 1307.4 TFLOPS
Bandwidth: 5.3 TB/s

Reserve a cluster Deploy H200 instead

Full pricing details

At a glance

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

Memory

NVIDIA B300288 GB

AMD MI300X192 GB

Memory bandwidth

NVIDIA B300up to 8.0 TB/s

AMD MI300X5.3 TB/s

FP16 tensor

NVIDIA B3002250 TFLOPS

AMD MI300X1307.4 TFLOPS

FP32

NVIDIA B30075 TFLOPS

AMD MI300X163 TFLOPS

Full specs

The complete spec sheet.

Spec	NVIDIA B300	AMD MI300X
Architecture	Blackwell	CDNA 3
Memory	288 GB	192 GB
Memory type	HBM3e	HBM3
Memory bandwidth	up to 8.0 TB/s	5.3 TB/s
FP32	75 TFLOPS	163 TFLOPS
FP16 tensor	2250 TFLOPS	1307.4 TFLOPS
INT8	187.5 TOPS	2610 TOPS
TDP	up to 1400 W	750 W
Form factor	SXM	OAM
NVLink	Yes	No
GPUs per node	8	8
Hourly price (live)	from $12.99/hr	Not in stock right now

Questions

B300 or MI300X. What buyers ask first.

Other comparisons