Datacenter GPUNVIDIA

NVIDIA GH200 (144GB HBM configuration)

Name: NVIDIA GH200 (144GB HBM configuration)
Brand: NVIDIA
SKU: gh200-144gb

Curated Aggregate·2024-08-042 workloads · 2 records

MyAI RatingNot scoredInsufficient comparison evidence

VRAM

144 GB

TDP

1000 W

MSRP

$45k

Perf/W

0.30 tok/s/W

Cost/1K tok

$0.0016/k

Tested

2024-08-04

Quick answer

How fast is NVIDIA GH200 (144GB HBM configuration) for local AI workloads?

NVIDIA GH200 (144GB HBM configuration) has a source-attributed result of 248.0 tok/s on Gemma 2 9B (batch 1, 8192-token context, Q4_K_M; runtime not documented). This is a reference report, not an independently verified lab result. A 70B Q4_K_M artifact needs roughly 40GB for weights alone; smaller memory configurations require explicit offload or model splitting and do not establish full-GPU residency.

Verdict

NVIDIA GH200 (144GB HBM configuration) with 144GB VRAM at 1000W TDP, scored across 2 workloads with 2 benchmark records.

Reference workload

Gemma 2 9B

248 tok/s

Quantization

Q4_K_M

8K context · batch 1

LLM Inference Performance

Benchmarks (2 workloads)

Workload	Score	Quant	Context	σ	Status	Tested
Mistral 7B llm	305.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-08-04
Gemma 2 9B llm	248.0tok/s	Q4_K_M	8K	,	Curated Aggregate	2024-10-26

MyAI Score: not scored

There is insufficient comparable evidence to score NVIDIA GH200 (144GB HBM configuration). A score needs results for multiple devices with matching workload, runtime version, quantization, context and batch size.

Workload Fit

Planning estimates for 144GB: weights plus at least 2GB or 10% overhead. Actual KV cache depends on model, context and cache format; confirm the artifact before buying.

FP16

7-8B

Excellent

13-14B

Excellent

32B

Excellent

70B

Excellent

Won't fit

Reported batch-one examples

Gemma 2 9B248 tok/s

Mistral 7B305 tok/s

Source

Gemma 2 9B GH200.

View source How we benchmark →

Public Trust Layer

Trust score

6/10

MyAI rating

Not scored

Runs

Not documented

Freshness

Stale

Source-linked row with explicit verification status.

Record date: 2024-10-26; 683 days old.

Open primary source

Enterprise buying note

Where to buy

Reseller compare

Retailer we'd check first

Amazon search plus reseller quotes

For datacenter and accelerator parts, Amazon is useful for spotting live listings, accessories, or used pulls, but serious procurement usually happens through integrators, brokers, or cloud partners.

Enterprise procurement, not retail

This silicon is typically acquired through an authorized OEM partner, system integrator, or hyperscaler reseller. For on-demand access, compare hourly rates at RunPod, Vast.ai, Lambda Labs, or your existing cloud provider before committing to capital expenditure.

+Use $45k only as a rough anchor. Enterprise street pricing moves with supply, warranty, and included accessories.
+Confirm cooling, power delivery, and return terms before you purchase. These parts often ship without consumer-friendly safeguards.
+If this is for production, compare against authorized reseller quotes before you commit.

There is insufficient comparable evidence for a purchase recommendation. Check model fit, software support and a current seller quote.

Affiliate note: we do not have a device-level ASIN yet, so this opens tagged Amazon search results for the exact product name.