NVIDIA H100 SXM 80GB
Unknown
CUDA cores
80 GB
VRAM
3,350 GB/s
Memory bandwidth
Data Center
Recorded Technical Specifications
- CUDA cores
- Unknown
- Base clock
- Unknown
- Boost clock
- Unknown
- Memory
- 80 GB; HBM3
- Memory bus
- Unknown
- Recorded TDP / board power
- 700 W
Recorded Performance
- Recorded FP32
- Unknown
- Recorded FP16
- Unknown
Measurement scope
Only source-verified benchmark fields are shown. Match precision, sparsity, form factor and test conditions before comparison; unknown means no verified measurement is recorded.
Cloud Catalogue
3 recorded offers; not live inventory
Recorded from $2.69/GPU-hour USD (runpod: H100 SXM 80GB; Community Cloud on-demand); confirm rate and stock
Compare Provider OffersH100 SXM 80GB Provider Offer Comparison
USD quotes; availability is not live. Compare matching variants and billing units.
| Provider | Configuration / billing | Recorded hourly price | GPU count | Recorded VRAM | Availability | Provenance |
|---|---|---|---|---|---|---|
| runpod | H100 SXM 80GB; Community Cloud on-demand | Recorded $2.69/GPU-hour USD | GPU count unknown | 80 GB (per GPU) | Availability unknown |
Verified 2026-10-31 www.runpod.io ↗EvidencePrice verified against source at 2026-10-31T23:54:57Z; not live inventory. Public advertised GPU-hour quote, not a stock check or total instance cost. GPU count, region, disk/network charges and final deployment terms require provider confirmation. |
| runpod | H100 SXM 80GB; Secure Cloud on-demand | Recorded $3.99/GPU-hour USD | GPU count unknown | 80 GB (per GPU) | Availability unknown |
Verified 2026-10-31 www.runpod.io ↗EvidencePrice verified against source at 2026-10-31T23:54:57Z; not live inventory. Public advertised GPU-hour quote, not a stock check or total instance cost. GPU count, region, disk/network charges and final deployment terms require provider confirmation. |
| lambda | H100 SXM 80GB; On-demand; plus applicable tax | Recorded $3.99/GPU-hour USD | GPU count unknown | 80 GB (per GPU) | Availability unknown |
Verified 2026-10-31 lambda.ai ↗EvidencePrice verified against source at 2026-10-31T23:54:57Z; not live inventory. Public advertised GPU-hour quote, not a stock check or total instance cost. GPU count, region, disk/network charges and final deployment terms require provider confirmation. |
Detailed Specifications
| Architecture | Hopper |
| GPU code name | Unknown |
| Recorded release date | Unknown |
| Recorded launch price (not rental) | Unknown |
| Manufacturing process | Unknown |
| Transistors | Unknown |
Specification review: 2026-11-01 · 9 source-verified fields · Cloud availability: unknown
Specification sources & scope
Only the listed fields are source-verified; other specifications remain unverified. Source review does not establish live availability.
- Source reviewed
- 2026-11-01
- Source-verified fields
- accelerator type, architecture, manufacturer, market segment, memory bandwidth, memory capacity, memory type, model, power consumption tdp
- Specification scope
- Single GPU; manufacturer reference specifications. Board-partner configurations may differ. Memory uses catalogue MiB units; bandwidth uses decimal GB/s; power is published board maximum.
- Lifecycle evidence
- Documented in manufacturer source; not a stock or shipping-status claim
- Lifecycle note
- Official manufacturer specifications reviewed; this is not a stock check, release-date verification or end-of-sale determination.
- Cloud rental availability
- Unknown — catalogue inclusion is not confirmation of rental stock
Manufacturer source links
https://www.nvidia.com/en-us/data-center/h100/Recorded AI features
Only source-verified fields are shown; unknown does not mean unsupported. Confirm hardware and software versions.
Tensor Cores
Unknown
Transformer Engine
Unknown
Flash Attention
Unknown
Software & workload notes
Allow memory for weights, optimizer state, KV cache and framework overhead. Core counts and nominal throughput are not directly comparable across architectures or manufacturers.
Recorded CUDA compute capability: Unknown. CUDA is NVIDIA-specific; confirm driver, toolkit and framework requirements against NVIDIA's documentation.
Partner listings · affiliate links
H100 SXM 80GB Partner Listings
We may earn a commission from these links. A recorded listing does not guarantee stock or current pricing.
RunPod
Recorded from $2.69/GPU-hour USD (runpod: H100 SXM 80GB; Community Cloud on-demand); confirm rate and stock
2 exact-model recorded offers; confirm price and availability.
Visit RunPod →Manufacturer & software references
Confirm support for the exact device, operating system and software version.
NVIDIA CUDA documentation ↗NVIDIA GPU compute capability reference ↗