← All hardware
The Hopper workhorse that powered the LLM boom, now widely available
Pros
- Widely available, no allocation wait
- Mature CUDA software stack
- Price has dropped sharply
- Proven at scale
Cons
- Two generations behind Blackwell
- 80GB limits largest models
- Less efficient per watt than newer parts
- Being phased out of new builds
✓ Where it shines / best for
- Mainstream LLM training/inference
- Cost-conscious AI clusters
- Fine-tuning
- Research labs
✕ Not the best fit for
- Frontier-scale new builds
- Maximum efficiency seekers
- Largest-context models
- Edge
Features
- ✓ Hopper architecture
- ✓ 80GB HBM3
- ✓ Transformer Engine (FP8)
- ✓ NVLink 4
- ✓ SXM and PCIe variants
- ✓ Massive software ecosystem
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| H100 80GB | ~$25,000-$40,000 | one-time | Stabilized Q1 2026; cloud from ~$1.25-$14.90/hr |
Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.
Specifications
| use | Data center training and inference |
| power | 350-700W |
| memory | 80GB HBM3, 3.35 TB/s |
| performance | ~4 PFLOPS FP8 (sparse) |
| architecture | Hopper (TSMC 4N) |
Sponsored
A full review is being generated for this product and will appear here shortly.