AMD Instinct MI300A 128GB vs AMD Instinct MI300X 192GB

The Instinct MI300X delivers 33% more FP8 throughput than the Instinct MI300A (2,615 vs 1,961 TFLOPS dense). The Instinct MI300X also carries 64 GB more memory (192 GB vs 128 GB).

Instinct MI300A: CDNA 3, 2023 Instinct MI300X: CDNA 3, 2023
FP8 dense lead
+33%
Instinct MI300X: 2,615 vs 1,961 TFLOPS
Memory
128 vs 192 GB
64 GB more for the Instinct MI300X
Bandwidth
5.3 TB/s vs 5.3 TB/s
Even
TDP
760 W vs 750 W
Instinct MI300X draws 10 W less
See rental pricing from $0.50/hr Download comparison sheet

Share this page

AMD Instinct MI300A 128GB vs AMD Instinct MI300X 192GB

A post with this link shows the card on the Image tab as its preview.

Printable version →

AMD Instinct MI300A 128GB

Full specs →

What is the AMD Instinct MI300A?

The Instinct MI300A is a GPU from AMD on the CDNA 3 architecture, an accelerator for AI training, inference and high-performance computing. Instinct MI300A full specifications →

Can I rent the Instinct MI300A in the cloud?

Flopper is not tracking any live rental listings for the Instinct MI300A yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Instinct MI300A compare with other accelerators?

This page sets the Instinct MI300A against the Instinct MI300X. Both parts launched in the same year. Both are AMD parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Instinct MI300A figures come from?

Every Instinct MI300A figure on this page traces to AMD's own datasheet or specification table. How Flopper verifies specifications →

AMD Instinct MI300X 192GB

Leads on FP8 Full specs →

What is the AMD Instinct MI300X?

The Instinct MI300X is a GPU from AMD on the CDNA 3 architecture, an accelerator for AI training, inference and high-performance computing. It is an OAM module, the open accelerator format used in multi-GPU servers. Instinct MI300X full specifications →

Can I rent the Instinct MI300X in the cloud?

Yes. Cloud providers tracked by Flopper rent the Instinct MI300X by the hour, and the pricing page compares their current rates and the price history side by side. Instinct MI300X rental prices →

How does the Instinct MI300X compare with other accelerators?

This page sets the Instinct MI300X against the Instinct MI300A. Both parts launched in the same year. Both are AMD parts. Flopper also compares it head to head with the H100 SXM5 80GB and H200 SXM 141GB, across every published precision, memory and power. Instinct MI300X vs H100 SXM5 80GB →

Where do the Instinct MI300X figures come from?

Every Instinct MI300X figure on this page traces to AMD's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Instinct MI300A
Instinct MI300X
Architecture
CDNA 3CDNA 3
Launch Year
20232023
Form Factor
APU SH5 socketOAM
Memory
128 GB192 GB
Memory Bandwidth
5.3 TB/s5.3 TB/s
TDP
760 W750 W
Process Node
5nm FinFET5nm FinFET

Performance (TFLOPS)

Instinct MI300A
Instinct MI300X
61 TFLOPS 82 TFLOPS
123 TFLOPS 163 TFLOPS
490 TFLOPS
981 TFLOPS sparse
654 TFLOPS
1,307 TFLOPS sparse
981 TFLOPS
1,961 TFLOPS sparse
1,307 TFLOPS
2,615 TFLOPS sparse
981 TFLOPS
1,961 TFLOPS sparse
1,307 TFLOPS
2,615 TFLOPS sparse
1,961 TFLOPS
3,922 TFLOPS sparse
2,615 TFLOPS
5,230 TFLOPS sparse
FP6
No verified data available No verified data available
No verified data available No verified data available
1,961 TOPS
3,922 TOPS sparse
2,615 TOPS
5,230 TOPS sparse

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

Both launched in 2023, the Instinct MI300A on CDNA 3 and the Instinct MI300X on CDNA 3.

The Instinct MI300X carries 64 GB more memory (192 GB against 128 GB), so larger models fit on one GPU before you shard. Bandwidth is 5.3 TB/s against 5.3 TB/s, which sets the ceiling on decode speed.

Power is 760 W against 750 W, and at FP32 the Instinct MI300X does more work per watt. Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP64, FP32, TF32, BF16, FP16, FP8, INT8, Sparsity and TFLOPS.

Frequently asked questions

Is the Instinct MI300A faster than the Instinct MI300X?

At FP8 precision the Instinct MI300X reaches 2,615 TFLOPS dense against 1,961 TFLOPS for the Instinct MI300A. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Instinct MI300A or the Instinct MI300X?

Choose the Instinct MI300X for training and high-throughput inference: it has 33% more FP8 throughput than the Instinct MI300A. It also carries 64 GB more memory, so larger models fit on one GPU before you shard. The Instinct MI300X draws 10 W less power, which matters in an air-cooled or power-capped rack.

Which has more memory, the Instinct MI300A or the Instinct MI300X?

The Instinct MI300X carries 192 GB of memory versus 128 GB for the Instinct MI300A. Memory bandwidth is 5.3 TB/s for the Instinct MI300A and 5.3 TB/s for the Instinct MI300X.

How much power do the Instinct MI300A and the Instinct MI300X draw?

The Instinct MI300A is rated at 760 W TDP and the Instinct MI300X at 750 W. On FP32 throughput per watt, the Instinct MI300X is the more efficient part.

How much do the Instinct MI300A and the Instinct MI300X cost to rent?

Live cloud listings tracked by Flopper price no live listings yet for the Instinct MI300A, and the Instinct MI300X from $0.50 per GPU-hour across 7 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

AMD Instinct MI300A 128GB

No live rental listings tracked for the Instinct MI300A yet.

Browse GPU cloud providers

AMD Instinct MI300X 192GB

Rent from

$0.50 / GPU-hr

Lowest of 16 live listings across 7 providers · median $3.22

See all Instinct MI300X rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

© 2026 Flopper.io - Compare the GPUs Powering AI