DEPLOYDatabase

AI chip · NVIDIA

NVIDIA H200 Tensor Core GPU

Hopper refresh with 141 GB HBM3e (from 80 GB); the mid-generation memory-bandwidth bump between H100 and Blackwell.

On the DEPLOY graph: 4 campuses carry a cited inventory line for it · 1 reference-design cluster include it.

Market position

H200 kept H100's compute silicon and swapped HBM3 for 141 GB HBM3e at 4.8 TB/s: 1.4x memory bandwidth in the same socket. Inference shops (Together AI, Perplexity, hyperscaler tenants) upgraded here first; training shops mostly held for Blackwell.

DEPLOY editorial. What the vendor PDF cannot tell you.

Physical-AI cross-link

Derived from claims already on record (vendor first-party TDP, throughput, price, and the reference-design cluster registry). The arithmetic is shown per row so it can be audited. No estimated inputs.

Perf per watt
2.83 FP8 TFLOPS/W
1,979 TFLOPS ÷ 700 W = 2.83
Rack power (in this design)
10.2 kW per NVIDIA HGX H200 (8-GPU baseboard) (~1275 W per chip incl. overhead)
10.2 kW ÷ 8 chips = 1275 W each (system-level, includes CPU/mem/NIC/cooling)
Cooling class (across reference designs)
air
Observed across 1 reference-design cluster containing this chip

What fits in 141 GB

Weights-only footprint for public open-weight LLMs. Pure arithmetic: params × bytes/param. Excludes KV cache and activation memory; add ~10-30% headroom for real serving. A model that does not fit at FP16 may still fit at INT8 or INT4 with quality trade-offs. Not a benchmark.

ModelParamsFP16INT8INT4
Llama 3.1 8B
dense
8 B16 GB ✓8 GB ✓4 GB ✓
Llama 3.1 70B
dense
70 B140 GB ✓70 GB ✓35 GB ✓
Llama 3.1 405B
dense
405 B810 GB ✗405 GB ✗203 GB ✗
Llama 3.3 70B
dense
70 B140 GB ✓70 GB ✓35 GB ✓
DeepSeek V3
MoE (671B total, 37B active per token)
671 B1342 GB ✗671 GB ✗336 GB ✗
DeepSeek R1
MoE (671B total, 37B active per token)
671 B1342 GB ✗671 GB ✗336 GB ✗
Qwen 2.5 7B
dense
7 B14 GB ✓7 GB ✓4 GB ✓
Qwen 2.5 72B
dense
72 B144 GB ✗72 GB ✓36 GB ✓
Mixtral 8x7B
MoE (46.7B total, 12.9B active per token)
46.7 B93 GB ✓47 GB ✓23 GB ✓
Mixtral 8x22B
MoE (141B total, 39B active per token)
141 B282 GB ✗141 GB ✓71 GB ✓
Gemma 2 27B
dense
27 B54 GB ✓27 GB ✓14 GB ✓
Command R+
dense
104 B208 GB ✗104 GB ✓52 GB ✓
Kimi K2
MoE (1T total, 32B active per token)
1000 B2000 GB ✗1000 GB ✗500 GB ✗

Math: FP16 = params × 2 bytes; INT8 = params × 1 byte; INT4 = params × 0.5 bytes. MoE models sum every expert (full weights on disk), not the per-token active subset.

Common questions

Answer-first, sourced. Every claim below traces to a specific field on this page or a cited datasheet. FAQPage schema is emitted so LLM crawlers can lift these verbatim.

How much does NVIDIA H200 Tensor Core GPU cost?

NVIDIA H200 Tensor Core GPU launch pricing is not on record in the DEPLOY registry. Vendor list prices are typically published in the vendor's own briefing rather than the datasheet.

How much memory does NVIDIA H200 Tensor Core GPU have?

141 GB of HBM3e at 4,800 GB/s. Vendor datasheet, first-party.

How much power does one NVIDIA H200 Tensor Core GPU draw?

700 W TDP (thermal design power) per chip. System-level draw is higher: see the reference-design section for rack-level kW.

Which data centers have NVIDIA H200 Tensor Core GPU?

4 campuses on the DEPLOY registry carry a cited inventory line for this chip. Full list below with per-campus quantity hints where published.

Which open-weight LLMs fit on one NVIDIA H200 Tensor Core GPU?

Of the 13 public open-weight LLMs DEPLOY tracks: 6 fit at FP16, 9 at INT8, 9 at INT4 (weights only, excludes KV cache). The full table is above with per-model math. Sparsity, offloading and multi-GPU serving change the picture; this row is single-chip weights-only.

Key facts

Class
Compute SoC (AI accelerator)
Designer
NVIDIA
Safety-critical?
No (data-center inference / training)
Record as of
2026-08-25
Latest cited claim
2026-01-15 (across 6 inventory + benchmark rows)
Specifications (17 fields, click to expand)

Vendor datasheet figures (first-party). Dense throughput first; sparse (2:4) in parentheses where NVIDIA quotes it. The exhaustive spec sheet lives on the datasheet URL below the table: this row set covers what buyers actually compare on.

Process node
TSMC 4N
Transistors
80 B
Die size
814 mm²
CUDA cores
16,896
Tensor cores
528 (4th gen (Hopper))
TDP
700 W
Memory
141 GB HBM3e
Memory bandwidth
4,800 GB/s
PCIe
Gen 5 x16 (900 GB/s)
FP32
67 TFLOPS
TF32 (dense)
495 TFLOPS
FP16 (dense)
989 TFLOPS (1,979 sparse)
FP8 (dense)
1,979 TFLOPS (3,958 sparse)
INT8 (dense)
1,979 TOPS (3,958 sparse)
Form factor
SXM5
Announced
2023-11-13
Released
2024-03-01

Source: vendor datasheet

Generation

Used in reference designs

The named rack-scale and pod-scale designs buyers actually order that contain this chip.

See all reference designs →

Compare with

See every chip comparison →

Benchmarks

Published measurements per workload. Vendor datasheet numbers are first-party (verified posture); MLPerf / InferenceX / press results come in when their license terms + workload naming permit.

WorkloadValueUnitSourceAs of
memory bandwidth4800GB/svendor2024-01-01
memory capacity141GB HBM3evendor2024-01-01

Data centers stocking NVIDIA H200 Tensor Core GPU

Who has the most? →

Every campus on the DEPLOY registry with a public claim of NVIDIA H200 Tensor Core GPU on site. Quantity hints are unstructured because underlying disclosures vary by order of magnitude.

  1. xAI Colossus (Memphis)as of 2026-01-15
    partially energizedreported

    Second-wave upgrade GPUs added late 2024

    Introl

  2. under constructioninferred

    H200/GB200-generation capacity for G42 / UAE AI stack

    G42 has committed multi-billion NVIDIA compute; per-campus attribution not published.

    Khazna

  3. Lake Mariner Data Campusas of 2025-01-01
    partially energizedinferred

    H200-generation HPC capacity for AI-training tenants

    AI-training-oriented HPC campus; specific chip mix not published, H200 inferred from current-gen positioning.

    TeraWulf

  4. Crusoe Childress Campusas of 2024-12-01
    announcedreported

    Recent Crusoe expansions include H200 capacity

    Crusoe

Sources

Adoption rows appear as we verify chip-integration claims per model. Every row is a public claim the maker or a tier-1 source has stated; verification tier (verified / reported / inferred) is shown per row. See every chip on record for the full catalog or the NVIDIA record.