Verdict
Head-to-head · Best AI Workstations

HP Z8 Fury G5 vs NVIDIA DGX Spark

Which is the better buy? Side-by-side on rating, price, strengths, and watch-outs — with the published ratings we averaged to get there.

The short answer

NVIDIA DGX Spark comes out ahead by a narrow margin (4.4 vs 4.6). The gap is mostly about Best for local-LLM developers — CUDA-native 128 GB dev box — read the strengths below before deciding.

HP Z8 Fury G5
Ranked #4 in Best AI Workstations
HP Z8 Fury G5
$7,995as of Apr 25

The HP Z8 Fury G5 is HP's flagship workstation — a formidable, highly scalable tower designed specifically for demanding professional media, VFX, and AI creators who need a four-GPU ceiling. Built around Intel's Xeon W9-3495X (56 cores), 128 GB DDR5 ECC, and up to four NVIDIA RTX A6000 cards, it is a credible local-LLM training and inference rig at the upper end. The configured price varies enormously: a 1-GPU base build lands around $7,995, a 2-GPU build around $14,000, and a fully loaded 4x RTX A6000 configuration pushes well past $25,000. The price field below reflects a typical 1-GPU configured build; readers planning multi-GPU AI work should expect to roughly triple that figure.

Strengths
  • Supports up to a four-GPU configuration for extreme parallel AI inference and tensor-parallel training
  • Features an easily accessible design with a built-in handle for serviceability
  • Offers a massive range of customization options for specific workloads
Watch-outs
  • Scaling up configurations becomes prohibitively expensive — 4x A6000 builds push $25,000+
  • Enormous tower chassis requires significant floor or desk space
  • Interior uses plain black plastic rather than premium materials
NVIDIA DGX Spark
Higher ratedRanked #2 in Best AI Workstations
NVIDIA DGX Spark
$4,699as of Apr 25

The NVIDIA DGX Spark is the productized version of Project DIGITS — a 150 mm cube housing the GB10 Grace Blackwell Superchip, 128 GB unified LPDDR5x, and the full CUDA AI stack out of the box. Tom's Hardware called it 'a well-rounded toolkit for local AI'; ServeTheHome called it 'must-have for AI developers'; LMSYS published the most thorough independent benchmarks. The 128 GB unified-memory ceiling is the headline feature: it loads models that would otherwise need a $30K+ multi-GPU rig. The catch is bandwidth-limited decode — LMSYS measured Llama-3.1 70B FP8 at 2.7 tokens/sec single-batch, while GPT-OSS 120B (MoE, ~17B active) hits ~14.5 tokens/sec per ServeTheHome. Best understood as a CUDA-native development box for buyers who need to iterate on big-model code without renting cloud GPUs.

Strengths
  • 128 GB unified LPDDR5x memory — fits 70B FP8 / 120B Q4 / 405B with two clustered units
  • Full CUDA + NVIDIA AI stack preinstalled; the most polished local-AI dev box on the market
  • Compact 150 mm cube, 240 W max — fits any desk, runs cool and quiet
Watch-outs
  • 273 GB/s LPDDR5x bandwidth caps decode tok/s on dense large models — 70B FP8 measures ~2.7 tok/s on a single unit
  • Linux-only, no Windows or gaming use; specialist hardware for AI developers
  • Price raised from $3,999 to $4,699 in February 2026 due to memory supply

How they stack up

HP Z8 Fury G5

Similar to the Dell Precision 7960 Tower, the HP Z8 Fury G5 supports four-GPU configurations for extreme parallel processing, but it differentiates itself with a built-in handle and a design prioritizing easy serviceability. Versus its smaller sibling the HP Z6 G5 A, the Z8 Fury G5 is the right pick when you genuinely need 4 GPUs (versus 3) or the Xeon W9 platform's enterprise ECC and reliability features. Versus the Puget Genesis II, the Z8 Fury G5 brings HP's enterprise service network and parts availability, while Puget brings hand-tuned assembly and a more thoughtful configurator. Versus the Apple Mac Studio M3 Ultra, the Z8 Fury G5 is twice the size and triple the price for a 1-GPU build, but unlocks training-class workloads the Mac Studio cannot touch.

NVIDIA DGX Spark

The DGX Spark is the cheapest path to 128 GB of CUDA-addressable unified memory anywhere on the market. Versus the GMKtec EVO-X2 ($1,699) or Beelink GTR9 Pro ($2,000), it's roughly 2.5x the price but offers the full NVIDIA software stack the Strix Halo boxes can only approximate via ROCm or Vulkan. Versus the Puget Genesis II ($10K+), it's a single-purpose dev box — no multi-display creative workflow, no gaming, no general workstation duty. Pair two Sparks via the ConnectX-7 networking and you get 405B-class model coverage at roughly $9,400, the cheapest legal path to that ceiling.

Specs side-by-side

SpecHP Z8 Fury G5NVIDIA DGX Spark
CPUIntel Xeon W9-3495X (56-core)20-core Arm (10x Cortex-X925 + 10x Cortex-A725)
GPUUp to 4x Nvidia RTX A6000 (192 GB pooled VRAM)NVIDIA GB10 Grace Blackwell Superchip
RAM128 GB DDR5 ECC (configurable to 2 TB)128 GB unified LPDDR5x
StorageNVMe SSD (configurable, multiple bays)4 TB NVMe M.2 (user-replaceable, self-encrypting)
Memory Bandwidth~307 GB/s system; ~768 GB/s per RTX A6000 VRAM273 GB/s
Form FactorFull towerCompact desktop (150 mm cube, 1.2 kg)
← See the full ranking of best ai workstations