H200 vs H100
The H200 and the H100 are both data centre GPUs we supply tested from Hong Kong, and the figures below are the same ones published on each product page. They share the same supply and warranty terms and separate on memory, architecture, mig, so the decision is less about "which is better" and more about which of those differences your platform or workload can actually use.
Nothing on this page is a price: used and refurbished hardware is repriced weekly, so both are quoted on request against confirmed stock with the date the quote holds until. If you are replacing a part, send the platform and we will confirm the population before you commit.
Side by side
H200 vs H100 specifications
| Specification | H200 | H100 |
|---|---|---|
| Memory | 141GB HBM3e, 4.8TB/s (both variants) | 80GB HBM3 3.35 TB/s (SXM5) / 80GB HBM2e 2.0 TB/s (PCIe) |
| Power | not stated | 700W (SXM5) / 350W (PCIe), passive |
| Architecture | Hopper GH100 with HBM3e memory | Hopper GH100, 132 SM (SXM5) / 114 SM (PCIe) |
| Compute | not stated | FP8 1,979 TFLOPS / FP16 989 TFLOPS (SXM5, with sparsity) |
| MIG | Up to 7 instances, 18GB each (SXM); 16.5GB each (NVL) | Up to 7 instances (10GB each) |
| NVLink | not stated | 900 GB/s GPU-to-GPU (SXM5); NVLink bridge (PCIe) |
| Model | NVIDIA H200 - SXM (HGX H200 baseboard) and H200 NVL (PCIe dual-slot) | NVIDIA H100 80GB — SXM5 (900-21010-0000-000) and PCIe variants |
| FP8 / INT8 Tensor Core | 3,958 TFLOPS (SXM) / 3,341 TFLOPS (NVL), with sparsity | not stated |
| BF16 / FP16 Tensor Core | 1,979 TFLOPS (SXM) / 1,671 TFLOPS (NVL), with sparsity | not stated |
| TF32 / FP32 / FP64 | 989 / 67 / 34 TFLOPS (SXM); 835 / 60 / 30 TFLOPS (NVL) | not stated |
| TDP | Up to 700W configurable (SXM); up to 600W configurable (NVL) | not stated |
| Interconnect | NVLink 900GB/s (SXM); PCIe Gen5 128GB/s plus 2- or 4-way NVLink bridge (NVL) | not stated |
| Form factor | SXM module for HGX baseboards; PCIe dual-slot air-cooled for NVL | not stated |
| Transformer Engine | not stated | FP8 training and inference, 4th-gen Tensor cores |
Rows that differ are highlighted. Figures are the same ones published on each product page; where a figure is community-sourced rather than vendor-published it is stated on that page. Confirm every part against your build sheet when ordering.
Where they differ
- ·Memory — H200: 141GB HBM3e, 4.8TB/s (both variants); H100: 80GB HBM3 3.35 TB/s (SXM5) / 80GB HBM2e 2.0 TB/s (PCIe).
- ·Architecture — H200: Hopper GH100 with HBM3e memory; H100: Hopper GH100, 132 SM (SXM5) / 114 SM (PCIe).
- ·MIG — H200: Up to 7 instances, 18GB each (SXM); 16.5GB each (NVL); H100: Up to 7 instances (10GB each).
Decision
Which one to buy
Data centre GPUs are chosen by memory footprint per job and by the deployment you already have. More memory per card means bigger models, larger batches and fewer cards for the same workload; less memory per card is often the better buy when you scale out across many nodes. Memory bandwidth and compute format matter for the workload — FP8 and BF16 throughput for inference, FP64 for simulation — and the power envelope decides how many cards fit per chassis. Check the form factor and cooling as well: a passive server card and an actively cooled workstation card are not interchangeable.
Choose the H200 if
- ·Memory: 141GB HBM3e, 4.8TB/s (both variants)
- ·Architecture: Hopper GH100 with HBM3e memory
- ·MIG: Up to 7 instances, 18GB each (SXM); 16.5GB each (NVL)
Choose the H100 if
- ·Memory: 80GB HBM3 3.35 TB/s (SXM5) / 80GB HBM2e 2.0 TB/s (PCIe)
- ·Architecture: Hopper GH100, 132 SM (SXM5) / 114 SM (PCIe)
- ·MIG: Up to 7 instances (10GB each)
Frequently asked questions
How much do the H200 and the H100 cost?
We do not publish prices for either: secondary-market hardware is repriced weekly. Send the quantity, the platform and the condition you want and we quote both against confirmed stock, with the date the figure holds until.
What is the main difference between the H200 and the H100?
Memory (H200: 141GB HBM3e, 4.8TB/s (both variants); H100: 80GB HBM3 3.35 TB/s (SXM5) / 80GB HBM2e 2.0 TB/s (PCIe)); Architecture (H200: Hopper GH100 with HBM3e memory; H100: Hopper GH100, 132 SM (SXM5) / 114 SM (PCIe)); MIG (H200: Up to 7 instances, 18GB each (SXM); 16.5GB each (NVL); H100: Up to 7 instances (10GB each)).
Can I use the H200 and the H100 in the same system?
They can share a server if the power and slot budget allows it, but they target different jobs: H200 and H100 differ mainly on Memory and Architecture. Mixed GPU models in one host is a driver/CUDA compatibility decision, not a hardware one.
Which one should I buy?
Buy the one whose strong points match the job: see the "Choose" section above. If you are replacing an existing part, send the platform or the old part number and we will confirm compatibility before you order.
What condition are they in, and do you ship worldwide?
Both are supplied tested with a 1-year written warranty. Condition is stated line by line before you order — new, decommissioned pull or OEM tray — and we ship worldwide from the Hong Kong warehouse with full export documentation, typically 3–7 days by air.
Get a quote for either — or both
Tell us the quantity, the platform and the condition you need. We confirm stock and put a firm figure in writing with the date it holds until.
Request a Quote