Overview
AMD MI325X
|
AMD MI455X
|
|
|---|---|---|
| Summary | Highest memory capacity AMD GPU for single-chip model serving. | AMD's CDNA 5 flagship for frontier-scale training and inference in Helios rack systems. |
| Architecture | CDNA3 | CDNA 5 |
| Memory | 256GB HBM3E | 432GB HBM4 |
| Memory Bandwidth | 6,000 GB/s | 23,300 GB/s |
| Performance | 2,615 TFLOPS (FP16) | 5,030 TFLOPS (FP16) |
| Release Date | Q4 2024 | Unknown |
| Performance Segment | High Performance | High Performance |
| Datasheet | Link | Link |
Price comparison
MI325X Pricing
We're tracking 5 cloud providers for the MI325X, and the pricing spread is significant. While the average sits at $2.30/hr, the lowest price is currently $1.57/hr per GPU (12-month reservation).
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click "View all offerings" to access the full list with sortable columns and filters for billing type, GPU count, vCPUs, and RAM.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Billing | Total/h | |
|---|---|---|---|---|
DigitalOcean
|
1x | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $2.88 | View |
Vultr
|
8x | Spot Variable spot pricing with potential interruptions. | $16.00 | View |
Bentaus
|
8x | On-Demand Pay-as-you-go pricing. No term commitments. | $18.00 | View |
Cyfuture AI
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.31 | View |
|
Bentaus
|
8x | Reservation Reserved pricing, contract term on request | $15.60 | View |
|
Cyfuture AI
|
2x | On-Demand Pay-as-you-go pricing. No term commitments. | $6.56 | View |
|
Cyfuture AI
|
1x | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $1.67 | View |
|
Cyfuture AI
|
1x | Reserved (6mo) Reserved capacity with a 6-month minimum commitment. | $2.01 | View |
|
Cyfuture AI
|
2x | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $3.21 | View |
|
Cyfuture AI
|
1x | Reserved (1mo) Reserved capacity with a 1-month minimum commitment. | $2.41 | View |
|
Cyfuture AI
|
2x | Reserved (6mo) Reserved capacity with a 6-month minimum commitment. | $3.89 | View |
|
Cyfuture AI
|
4x | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $6.36 | View |
|
Cyfuture AI
|
4x | On-Demand Pay-as-you-go pricing. No term commitments. | $12.97 | View |
|
Cyfuture AI
|
2x | Reserved (1mo) Reserved capacity with a 1-month minimum commitment. | $4.72 | View |
|
Cyfuture AI
|
4x | Reserved (6mo) Reserved capacity with a 6-month minimum commitment. | $7.70 | View |
| No offerings matching your filters. | ||||
MI455X Pricing
The MI455X is listed by 4 cloud providers, but none offer public on-demand pricing.
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click "View all offerings" to access the full list with sortable columns and filters for billing type, GPU count, vCPUs, and RAM.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Billing | Total/h | |
|---|---|---|---|---|
TensorWave
|
1x | Custom Accepting reservations, pricing TBD | Custom | View |
Cirrascale
|
1x | Custom Announced for the AI Innovation Cloud, pricing TBD | Custom | View |
Azure
|
1x | Custom Custom terms negotiated with the provider. | Custom | View |
|
Vultr
|
1x | Custom Custom terms negotiated with the provider. | Custom | View |
| No offerings matching your filters. | ||||
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Alternative GPUs
Here's how these GPUs compare against alternatives:
AMD MI325X
vs
AMD MI300X
AMD MI325X
vs
Nvidia H200
AMD MI455X
vs
AMD MI355X
AMD MI455X
vs
Nvidia B300
Our data for AMD MI325X was last updated on March 25, 2026, and for AMD MI455X on July 27, 2026.