Specifications Compared
| Spec | A100 SXM4 40GB | MI300X |
|---|---|---|
| TDP | 400W | 750W |
| VRAM | 40 GB | 192 GB |
| CUDA Cores | 6,912 | Not published |
| FP8 (dense) | Not published | 2,614.9 TFLOPS |
| Memory Type | HBM2e | HBM3 |
| Architecture | Ampere | CDNA 3 |
| FP16 (dense) | 312 TFLOPS | 1,307.4 TFLOPS |
| Form Factors | SXM4 | OAM |
| INT8 (dense) | 624 TOPS | 2,614.9 TOPS |
| Interconnect | NVLink, PCIe 4.0, InfiniBand | Infinity Fabric, PCIe 5.0 |
| Tensor Cores | 432 | Not published |
| FP32 Performance | 19.5 TFLOPS | 163.4 TFLOPS |
| FP64 Performance | 9.7 TFLOPS | 81.7 TFLOPS |
| Memory Bandwidth | 2,039 GB/s | 5,300 GB/s |
| FP8 (with sparsity) | Not published | 5,229.8 TFLOPS |
| FP16 (with sparsity) | 624 TFLOPS | 2,614.9 TFLOPS |
| INT8 (with sparsity) | 1,248 TOPS | 5,229.8 TOPS |
Performance Analysis
FP16 dense throughput measures 312 TFLOPS on the A100 SXM4 40GB against 1,307.4 TFLOPS on the MI300X while FP16 with sparsity measures 624 TFLOPS against 2,614.9 TFLOPS. FP32 throughput measures 19.5 TFLOPS on the A100 SXM4 40GB against 163.4 TFLOPS on the MI300X. Memory bandwidth of 2,039 GB/s on the A100 SXM4 40GB versus 5,300 GB/s on the MI300X supports larger batch sizes during training and inference on the MI300X while the 40 GB versus 192 GB capacity limits model scale on the A100 SXM4 40GB.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
A100 SXM4 40GB
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| LeaderGPU | The Netherlands | 8 | $0.68 | $5.42 | Deploy |
| Vast.ai | Czechia, CZ | 1 | $0.73 | — | Deploy |
| ThunderCompute | USA | 1 | $1.09 | — | Deploy |
| Hyperstack | CANADA-1 | 4 | $1.35 | $5.40 | Deploy |
| Massed Compute | us-east-1 | 1 | $1.38 | — | Deploy |
10 providers in stock, 33 offers (cheapest per provider shown). All A100 SXM4 40GB offers, price history and alerts
MI300X
1 provider in stock, 1 offer. All MI300X offers, price history and alerts
Notify me when A100 SXM4 40GB drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.68/GPU-hr.
QuantaCloud
Comparing A100 providers? We broker across all of them.
Need 16+ A100s reserved for fine-tuning, simulation, or production inference? We quote volume pricing across multiple data center partners: one quote at partner rates, 24h turnaround.
When to Choose the A100 SXM4 40GB
The A100 SXM4 40GB suits deployments constrained to 400 W TDP and existing NVLink fabrics. Its 40 GB HBM2e capacity and SXM4 form factor fit established PCIe 4.0 or InfiniBand clusters where lower power density is required.
When to Choose the MI300X
The MI300X suits workloads that require 192 GB HBM3 capacity and 5,300 GB/s bandwidth. Its OAM form factor and Infinity Fabric interconnect align with new installations that accommodate 750 W TDP and PCIe 5.0.
Use Cases
The MI300X supplies 192 GB HBM3 and 1,307.4 TFLOPS FP16 dense throughput that accommodate larger models than the 40 GB and 312 TFLOPS of the A100 SXM4 40GB.
The MI300X delivers 2,614.9 TFLOPS FP8 dense throughput and 5,300 GB/s bandwidth that support higher throughput than the A100 SXM4 40GB specifications.
The MI300X 192 GB capacity permits fine-tuning of models that exceed the 40 GB limit of the A100 SXM4 40GB.
The MI300X memory bandwidth of 5,300 GB/s accelerates diffusion workloads beyond the 2,039 GB/s of the A100 SXM4 40GB.
The A100 SXM4 40GB at 400 W TDP fits power limited clusters while the MI300X at 163.4 TFLOPS FP32 suits higher performance needs.
Frequently Asked Questions
What memory capacities distinguish the A100 SXM4 40GB from the MI300X?▾
The A100 SXM4 40GB provides 40 GB HBM2e while the MI300X provides 192 GB HBM3. These capacities remain fixed across variants within each family.
How do the FP16 dense figures compare between the two GPUs?▾
The A100 SXM4 40GB reaches 312 TFLOPS FP16 dense while the MI300X reaches 1,307.4 TFLOPS FP16 dense. Both figures represent dense performance without sparsity.
What are the TDP ratings for the A100 SXM4 40GB and MI300X?▾
The A100 SXM4 40GB operates at 400 W TDP. The MI300X operates at 750 W TDP. These values apply across the respective families.
How does memory bandwidth differ between the GPUs?▾
The A100 SXM4 40GB provides 2,039 GB/s bandwidth. The MI300X provides 5,300 GB/s bandwidth. Both figures represent family wide specifications.
Which is cheaper to rent, the A100 SXM4 40GB or the MI300X?▾
Cloud rental prices for both the A100 SXM4 40GB and MI300X vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the A100 SXM4 40GB have compared to the MI300X?▾
The A100 SXM4 40GB has 40 GB of HBM2e memory. The MI300X has 192 GB of HBM3 memory.
Can I find A100 SXM4 40GB and MI300X GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the A100 SXM4 40GB and the MI300X?▾
The A100 SXM4 40GB uses the Ampere architecture (2020) while the MI300X uses CDNA 3 (2023). The MI300X delivers 4.2x the dense FP16 throughput (1,307.4 vs 312 TFLOPS, both without sparsity) and 2.6x the memory bandwidth of the A100 SXM4 40GB.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the A100 SXM4 40GB and the MI300X. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent A100Every current offer by provider, daily price history and a price alert.
- Rent MI300XEvery current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.