NVIDIA H200 NVL
Dual-slot PCIe form factor of the H200 with the same 141 GB HBM3e memory and 4.8 TB/s bandwidth as the SXM variant. Lower TDP (600 W vs 700 W) makes it a drop-in upgrade for existing PCIe servers, with NVLink Bridge support between paired cards.
VRAM
141 GB
Memory
HBM3e
Bandwidth
4,800 GB/s
FP16
1,671 TF
TDP
600 W
Memory and compute
Architecture and power
Notes
Compute throughput shown with 2:4 structured sparsity. ~84% of H200 SXM compute due to lower TDP.
Models that may fit on NVIDIA H200 NVL
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
More GPUs by NVIDIA
The manufacturer's other cards in the catalog, largest memory first, with bandwidth and power where published.
Frequently asked questions about NVIDIA H200 NVL
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
NVIDIA H200 NVL has 141 GB of HBM3e at 4,800 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 112B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Gemma 4 31B IT, Llama Nemotron Embed VL 1B V2, GLM Z1 9B 0414 and NVIDIA Nemotron Nano 12B V2 VL BF16 fit on a single NVIDIA H200 NVL with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
4,800 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 112B model at INT8 could be read on the order of 43 times a second on one card, before batching and framework efficiency.
NVIDIA H200 NVL has a TDP of 600 W, with a maximum of 600 W, in the PCIe form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
NVIDIA H200 NVL is a datacenter accelerator, meant for servers and multi-GPU serving, built on the Hopper architecture and released in 2024. It supports a multi-GPU interconnect at 900 GB/s, so a model larger than one card can be split across several.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Apr 30, 2026 · Last updated Apr 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.