A100 80GB SXM vs Instinct MI300X
Side-by-side comparison of the NVIDIA A100 80GB SXM and the AMD Instinct MI300X for AI inference workloads.
Specifications
| Spec | A100 80GB SXM | Instinct MI300X |
|---|---|---|
| Generation | ampere | cdna3 |
| Memory Type | HBM2e | HBM3 |
| VRAM | 80 GB | 192 GB |
| Memory Bandwidth | 2,039 GB/s | 5,300 GB/s |
| BF16 TFLOPS | 312 | 1,307 |
| FP16 TFLOPS | 312 | 1,307 |
| FP8 TFLOPS | 312 | 2,614 |
| INT8 TOPS | 624 | 2,614 |
| TDP | 400 W | 750 W |
| Interconnect | nvlink | infinity-fabric |
| NVLink Bandwidth | 600 GB/s | N/A |
| Max GPUs per Node | 8 | 8 |
| PCIe Gen | Gen 4 | Gen 5 |
| CUDA Compute Capability | 8 | N/A |
Pricing
A100 80GB SXM
| Provider | On-Demand | Reserved | Spot |
|---|---|---|---|
| runpod | $2.72/hr | - | $2.09/hr |
| lambda | $1.99/hr | $1.49/hr | - |
| coreweave | $2.21/hr | $1.62/hr | - |
| aws | $3.67/hr | $2.39/hr | - |
| gcp | $3.67/hr | $2.48/hr | - |
| azure | $3.67/hr | $2.45/hr | - |
| vast ai | $1.80/hr | - | $1.30/hr |
| tensordock | $1.79/hr | - | $1.29/hr |
| fluidstack | $1.69/hr | - | $1.19/hr |
Instinct MI300X
| Provider | On-Demand | Reserved | Spot |
|---|---|---|---|
| runpod | $3.49/hr | - | $2.59/hr |
| lambda | $2.49/hr | - | - |
| coreweave | $3.39/hr | $2.49/hr | - |
| vast ai | $2.79/hr | - | $1.99/hr |
| tensordock | $2.69/hr | - | $1.99/hr |
| fluidstack | $2.39/hr | - | $1.79/hr |
Cheapest available rate: A100 80GB SXM at $1.19/hr vs Instinct MI300X at $1.79/hr — A100 80GB SXM is +50% cheaper
Efficiency Metrics
TFLOPS / Watt
0.8
A100 80GB SXM
1.7
Instinct MI300X
BF16
VRAM / Dollar
67.2
A100 80GB SXM
107.3
Instinct MI300X
GB/$/hr
Bandwidth / Watt
5.1
A100 80GB SXM
7.1
Instinct MI300X
GB/s/W
Models (FP16, 1 GPU)
182.0
A100 80GB SXM
221.0
Instinct MI300X
Model Compatibility (FP16, Single GPU)
Only on A100 80GB SXM (0)
None
Both (182)
- Yi 1.5 34B
- Yi 1.5 9B
- Yi Coder 9B
- GTE Qwen2 7B
- Marco O1
- Qwen 1.5 MoE A2.7B
- Qwen 2 Audio 7B
- Qwen 2.5 14B
- Qwen 2.5 32B
- Qwen 2.5 3B
- Qwen 2.5 Coder 32B
- OLMo 2 13B
- OLMo 2 7B
- Amazon Nova Lite
- OpenELM 3B
- BGE Large EN v1.5
- BGE M3
- Baichuan 2 13B
- OctoCoder 15B
- StarCoder2 15B
- +162 more
Only on Instinct MI300X (39)
- Jamba 1.5 Mini
- Amazon Nova Pro
- Code Llama 70B
- Dolphin 2.9 72B
- DeepSeek R1 Distill 70B
- Falcon 40B
- Llama 3 70B 1M Context
- Llama 2 70B
- Llama 3 70B
- Llama 3.1 70B
- Llama 3.3 70B
- WizardMath 70B
- Mixtral 8x7B
- Hermes 3 70B
- HelpSteer2 Llama 3.1 70B
- Llama 3.1 Nemotron 51B
- Llama 3.1 Nemotron 70B Instruct
- Llama 3.1 Nemotron 70B Reward
- Nemotron 70B
- VILA 1.5 40B
- +19 more
Summary
The A100 80GB SXM (ampere generation) offers 80GB of HBM2e with 312 BF16 TFLOPS and 2,039 GB/s memory bandwidth at 400W TDP.
The Instinct MI300X (cdna3 generation) offers 192GB of HBM3 with 1,307 BF16 TFLOPS and 5,300 GB/s memory bandwidth at 750W TDP.
The Instinct MI300X has +140% more VRAM, allowing it to run larger models without multi-GPU setups.
From a cost perspective, the A100 80GB SXM is more affordable at $1.19/hr vs $1.79/hr for the Instinct MI300X.