MI300X vs B200: specifications compared
Comparison of MI300X and B200 based on data from the manufacturer or provider.
According to the manufacturer, MI300X and B200 differ mainly in memory bandwidth (MI300X: 5,300 GB/s, B200: 8,000 GB/s), power (TDP) (MI300X: 750 W, B200: 1,000 W) and memory (MI300X: 192 GB, B200: 180 GB). The architecture also differs: CDNA 3 versus Blackwell. Checked on 19 October 2026, no prices.
How are the points calculated?
Clouwino points are an arithmetic summary of the specifications the manufacturer states, on a scale of 0 to 100. It is not a benchmark and not a judgement on quality or suitability: a product with fewer points may suit your situation better. Products are compared with other products of the same type. For each property we count how far a product sits between the lowest and highest value in the group:
- FP32 compute (for: consumer), carries heavy weight
- Memory (for: consumer), carries heavy weight
- Memory bandwidth (for: consumer), carries heavy weight
- Compute units (for: consumer), carries light weight
- Boost clock (for: consumer), carries light weight
- Memory (for: professional and data centre), carries medium weight
- Memory bandwidth (for: professional and data centre), carries medium weight
- FP16/BF16 (for: professional and data centre), carries heavy weight
- FP8 (for: professional and data centre), carries medium weight
- FP64 (for: professional and data centre), carries medium weight
If too much data is missing, we do not show points. Points are relative: when a new product is added, they can shift. Read more at how we compare.
MI300X and B200 side by side
| Specificatie | AMD Instinct MI300X | NVIDIA B200 (HGX B200) |
|---|---|---|
| Overview | ||
| Clouwino points | 51 punten | Not stated by the manufacturer |
| General | ||
| Architecture | CDNA 3 | Blackwell |
| Manufacturing process | TSMC 5nm | 6nm FinFET | TSMC 4NP |
| Form | OAM | SXM (HGX B200, 8x Blackwell SXM) |
| Launch | Not stated by the manufacturer | 2024-03 |
| Compute | ||
| FP32 compute | 163,4 TFLOPS | Not stated by the manufacturer |
| FP64 | 81,7 TFLOPS | Not stated by the manufacturer |
| FP16/BF16 | 1.300 TFLOPS | Not stated by the manufacturer |
| FP8 | 2.610 TFLOPS | Not stated by the manufacturer |
| FP4 | Not stated by the manufacturer | Not stated by the manufacturer |
| Performance notes | AMD shows dense and 'with structured sparsity'. FP16 and BF16: 1.3 PFLOPS dense (2.61 PFLOPS sparse). FP8 (E5M2/E4M3): 2.61 PFLOPS dense (5.22 PFLOPS sparse). FP64 81.7 TFLOPS vector (matrix 163.4); FP32 163.4 TFLOPS (vector and matrix). PFLOPS converted to TFLOPS (unit only; AMD rounds to 1.3). FP4 not supported/stated. | On its product pages NVIDIA only publishes figures for the 8-GPU HGX/DGX B200 system, not per-GPU figures; conversion is not permitted, so all compute performance fields are null. System values HGX B200 (8 GPUs): FP4 144 PFLOPS sparse / 72 PFLOPS dense; FP8 72 PFLOPS sparse (dense = half); FP16/BF16 36 PFLOPS sparse; TF32 18 PFLOPS sparse; INT8 72 POPS sparse; FP32 600 TFLOPS; FP64/FP64 Tensor Core 296 TFLOPS. |
| Memory | ||
| Memory | 192 GB | 180 GB |
| Memory type | HBM3 | HBM3e |
| Memory bandwidth | 5,3 TB/s | 8 TB/s |
| Power and connections | ||
| Power (board power or TDP) | 750 W | 1.000 W |
| GPU interconnect | 8x Infinity Fabric, 128 GB/s per link; PCIe 5.0 x16 | NVLink 5: 1.8 TB/s GPU-to-GPU |
| Multiple instances | Not stated by the manufacturer | Not stated by the manufacturer |
Note: Figures are per GPU. 'Typical board power' 750 W peak. Bandwidth 5.3 TB/s (footnote 5.325 TB/s). Partitioning not described (SR-IOV only), so multi_instance is null. Launch date is not stated unambiguously on the page.
Note: Memory (180 GB), bandwidth (up to 8 TB/s) and 'configurable up to 1 kW per GPU' come from NVIDIA reference architecture documentation (docs.nvidia.com), not from a datasheet table; the DGX B200 page states 1,440 GB and 64 TB/s for 8 GPUs. TDP is a maximum (configurable). Process node: NVIDIA states a custom TSMC 4NP process for Blackwell GPUs (press release 18 March 2024). Launch date = announcement 18 March 2024 (GTC).
Main differences between MI300X and B200
These are the differences the manufacturer lists in the specifications. The full table is further down.
- Memory bandwidth: MI300X 5,300 GB/s, B200 8,000 GB/s. B200 lists about 51% more.
- Power (TDP): MI300X 750 W, B200 1,000 W. B200 lists about 33% more.
- Memory: MI300X 192 GB, B200 180 GB. MI300X lists slightly more.
- Architecture: MI300X CDNA 3, B200 Blackwell.
- Memory type: MI300X HBM3, B200 HBM3e.
- Form factor: MI300X OAM, B200 SXM (HGX B200, 8x Blackwell SXM).
What should you look at when choosing?
A higher number is not better for everyone. It depends on what you want to use it for.
- Memory bandwidth. Higher bandwidth means data can move to and from memory faster.
- Power (TDP). A higher power rating calls for a suitable power supply and cooling, and can use more electricity.
- Memory. Memory determines how much data the GPU can hold at once, for example large models, datasets or textures.
Also look at the rest of your system, such as power supply, cooling and software. Real-world performance depends on more than the specifications alone.
Why are there no points?
For one or both products there is too little comparable data in the manufacturer’s specifications to calculate points. We prefer to show no number then. Read how we calculate them at How we compare.
Frequently asked questions
What is the difference between MI300X and B200?
According to the manufacturer, MI300X and B200 differ mainly in memory bandwidth (MI300X: 5,300 GB/s, B200: 8,000 GB/s), power (TDP) (MI300X: 750 W, B200: 1,000 W) and memory (MI300X: 192 GB, B200: 180 GB). The architecture also differs: CDNA 3 versus Blackwell.
Which one has the highest memory bandwidth?
According to the manufacturer, B200 lists the highest memory bandwidth: 8,000 GB/s versus 5,300 GB/s.
What do MI300X and B200 cost?
Clouwino does not show prices. You can see the current price and availability with the partner, via the button on the product page.
Where does the data come from?
The specifications come from the manufacturers' official pages and were checked on 19 October 2026. The sources are at the bottom of this page.
Last updated on
