CDNA 3
AMD Instinct MI300X
wins
5
The AMD MI300X leads all GPUs on memory capacity (192GB HBM3) and bandwidth (5.3 TB/s), making it exceptional for serving very large language models that don't fit on H100.
Hopper
NVIDIA H100 80GB
wins
1
The NVIDIA H100 is the gold standard for AI training and inference. With 80GB HBM3 memory and NVLink 4.0 support, it dominates large-model training and multi-GPU clusters.
Performance comparison
Visual bars — winner highlighted
AMD Instinct MI300X
Metric
NVIDIA H100 80GB
FP16 TFLOPS
Bandwidth
VRAM
TDP (lower=better)
TFLOPS/watt
GB/s per watt
TFLOPS/$
FP16 TFLOPS ÷ best on-demand $/hr
GB/s per $
Memory bandwidth ÷ best on-demand $/hr
Full specification table
| Spec | AMD Instinct MI300X | NVIDIA H100 80GB |
|---|---|---|
| Architecture | CDNA 3 | Hopper |
| VRAM | 192 GB HBM3 | 80 GB HBM3 |
| VRAM type | HBM3 | HBM3 |
| Memory bandwidth | 5,300 GB/s | 3,350 GB/s |
| FP16 TFLOPS | 1,307 TFLOPS | 989 TFLOPS |
| TDP | 750 W | 700 W |
| TFLOPS/watt | 1.74 T/W | 1.41 T/W |
| GB/s per watt | 7.07 GB/s/W | 4.79 GB/s/W |
| NVLink | No | Yes |
| Release year | 2023 | 2022 |
| Best cloud price | $1.85/hr | $2.85/hr |
| TFLOPS/$ | 706.5 | 347.0 |
| GB/s per $ | 2865 | 1175 |
Live cloud pricing
On-demand pricing across providers — updated in real time
AMD Instinct MI300X
NVIDIA H100 80GB
Power efficiency analysis
TFLOPS/watt and GB/s/watt — critical for data center TCO
AMD Instinct MI300X
NVIDIA H100 80GB
TFLOPS/watt measures compute efficiency — how much AI throughput you get per watt of power consumed. For data centers with PUE of 1.2–1.5, a 10% improvement in TFLOPS/watt translates directly to lower electricity costs and cooling requirements. GB/s/watt measures memory bandwidth efficiency, which is the binding constraint for memory-bound LLM inference workloads.
Performance-per-dollar
TFLOPS/$ and GB/s/$ at current best cloud prices
AMD Instinct MI300X
NVIDIA H100 80GB
TFLOPS/$ = FP16 TFLOPS ÷ best on-demand $/hr. Higher is better — more compute per dollar. GB/s/$ = memory bandwidth ÷ best on-demand $/hr. For memory-bound inference workloads (most LLM serving), GB/s/$ is often a better predictor of cost-efficiency than TFLOPS/$. Prices are live from the Compute Comparison API and update in real time.
Workload Cost Comparison
Total job cost = best on-demand $/hr × GPU count × hours
| Workload | Scale | AMD Instinct MI300X | NVIDIA H100 80GB |
|---|---|---|---|
| 7B LLM fine-tune | 8× GPU, 24 h | $355▼ | $547 |
| 70B LLM fine-tune | 64× GPU, 72 h | $8.5k▼ | $13k |
| Inference server | 1× GPU, 730 h | $1.4k▼ | $2.1k |
| Image gen batch | 4× GPU, 8 h | $59▼ | $91 |
Based on current best on-demand prices. Spot pricing typically 40–70% lower. Actual cost depends on provider, region, and availability.
When to choose each GPU
Choose AMD Instinct MI300X for:
- Memory-bound LLM inference
- Large model serving
- HPC
Weaknesses / Limitations
- ROCm software ecosystem is less mature than CUDA — some frameworks require extra porting effort
- Fewer cloud providers offer MI300X compared to H100
- 750W TDP — high power draw comparable to H100 SXM
Choose NVIDIA H100 80GB for:
- LLM training
- Large-scale inference
- HPC workloads
Weaknesses / Limitations
- Highest rental cost of any widely available GPU
- SXM form factor requires NVLink-capable server chassis
- 700W TDP demands high-density power and cooling infrastructure
Popular GPU comparisons