NVIDIA H200 NVL (PCIe)
No editorial image yet — generic vendor mark shown. Credentials in spec table below.
The PCIe-form-factor variant of the H200. Same 141 GB HBM3e, same memory subsystem (~4.8 TB/s bandwidth), in a dual-slot workstation card rather than the SXM5 datacenter module. For operators who want H200-class capacity in a standard PCIe slot (workstation deployments, single-node serving), the NVL is the realistic path. Two cards in NVLink Bridge pair to act as an effective 282 GB pool.
Affiliate disclosure: as an Amazon Associate and partner of other retailers, we earn from qualifying purchases. The verdict on this page is our editorial opinion; affiliate links never influence what we recommend.
Sub-scores sum to 977 / 1000. Headline = 977 × 0.70 (Estimated-confidence discount) = 684. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →
Extrapolated from 4800 GB/s bandwidth — 576.0 tok/s estimated. No measured benchmarks yet.
Plain-English: Runs 70B comfortably — snappy enough for a coding agent; vision models supported.
Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.
Overview
The PCIe-form-factor variant of the H200. Same 141 GB HBM3e, same memory subsystem (~4.8 TB/s bandwidth), in a dual-slot workstation card rather than the SXM5 datacenter module. For operators who want H200-class capacity in a standard PCIe slot (workstation deployments, single-node serving), the NVL is the realistic path. Two cards in NVLink Bridge pair to act as an effective 282 GB pool. Realistic deployment: production inference serving via vLLM or TensorRT-LLM, large-context RAG over enterprise corpora, 70B-class fine-tuning. Not for consumer rigs.
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
The NVIDIA H200 NVL (PCIe) is a datacenter GPU. Most people rent it by the hour rather than buy one. Which cards are listed, and at what hourly rate, changes all the time, so check the listing before you start.
Referral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. How we make money.
Specs
| VRAM | 141 GB |
| Power draw (peak) | 600 W |
| Released | 2024 |
| Backends | CUDA |
Models that fit
Open-weight models small enough to run on NVIDIA H200 NVL (PCIe) with usable context.
Frequently asked
What models can NVIDIA H200 NVL (PCIe) run?
Does NVIDIA H200 NVL (PCIe) support CUDA?
Where next?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.