NVIDIA DGX Station GB300 (748 GB)

A deskside Grace Blackwell Ultra system with 252 GB of HBM3e and 496 GB of LPDDR5X joined into 748 GB of coherent memory over NVLink-C2C. It is the first desktop-sized NVIDIA system in the catalogue that can hold trillion-parameter-class models at aggressive quantization.

NVIDIAappliance27 models fit0 measured
Memory
748 GB
Official spec 252 GB HBM3e + 496 GB LPDDR5X coherent
Memory bandwidth
7,100 GB/s
Official spec ~15% achieved in practice
Specifications
CPU
NVIDIA Grace, 72-core Arm Official spec
GPU
NVIDIA GB300 Blackwell Ultra Official spec
Memory
748 GB 252 GB HBM3e + 496 GB LPDDR5X coherent Official spec
Memory bandwidth
7,100 GB/s Official spec source
Achieved bandwidth
~15% (1,065 GB/s) Assumption
FP16 compute
~2,500 TFLOPS Official spec
Interconnect
NVLink-C2C coherent memory Official spec
Architecture
Unified memory (CPU and GPU share one pool) Official spec
Nominal power
1600 W Official spec
Measured load power
1350 W Measured
Idle power
180 W Measured
Released
28 Aug 2026 Official spec
Official capacity is 748 GB coherent: 252 GB HBM3e at 7.1 TB/s plus 496 GB CPU LPDDR5X over NVLink-C2C. The displayed 7.1 TB/s is the fast HBM tier, not uniform bandwidth across the full pool; the deliberately conservative achieved-bandwidth coefficient accounts for models spilling into LPDDR. Price and typical draw are ESTIMATES; NVIDIA specifies a 1,600 W system power budget.
Model performance on NVIDIA DGX Station GB300 (748 GB)0 measured, 27 estimated
27 of 27 rows
ModelQuantMemoryDecodePrefillContextFitConfidence
gpt-oss-20b
OpenAI · 20.915B (3.6B active)
MXFP413.0 GB~263–379 t/s~82400–171140 t/s128KComfortableEstimated
gpt-oss-120b
OpenAI · 116.829B (5.1B active)
MXFP466.5 GB~205–296 t/s~29290–60840 t/s128KComfortableEstimated
Qwen3-Coder 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q8_033.5 GB~168–242 t/s~35620–73970 t/s256KComfortableEstimated
Qwen3 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q8_033.5 GB~168–242 t/s~35620–73970 t/s40KComfortableEstimated
Gemma 4 26B-A4B
Google DeepMind · 25.806B (3.8B active)
Q8_029.7 GB~150–216 t/s~36100–74980 t/s256KComfortableEstimated
Qwen3.8 Flash Next
Alibaba Qwen · 180B (6B active)
Q8_0188.9 GB~102–147 t/s~10880–22590 t/s256KComfortableEstimated
Qwen3 8B
Alibaba Qwen · 8.191B
Q8_010.6 GB~89.4–129 t/s~43650–90650 t/s40KComfortableEstimated
DeepSeek-V4.1 Flash
DeepSeek · 763.205B (16B active)
Q4_K_M458.2 GB~70–101 t/s~3240–6720 t/s1024KComfortableEstimated
Qwen3.5 122B-A10B
Alibaba Qwen · 125.086B (10B active)
Q8_0131.8 GB~64.4–92.6 t/s~10110–20990 t/s256KComfortableEstimated
Phi-4 14B
Microsoft · 14.66B
Q8_017.8 GB~52.5–75.5 t/s~24390–50650 t/s16KComfortableEstimated
DeepSeek-V4 Flash
DeepSeek · 304.18B (13B active)
Q8_0317.9 GB~50.4–72.6 t/s~5690–11810 t/s1024KComfortableEstimated
GLM-5.3 Flash
Z.ai · 321.323B (18B active)
Q8_0335.4 GB~37.1–53.3 t/s~4700–9760 t/s1024KComfortableEstimated
Kimi K2.6
Moonshot AI · 1.0T (32B active)
Q4_K_M616.6 GB~36.6–52.6 t/s~1970–4100 t/sBorderlineEstimated
Devstral Small 24B
Mistral AI · 23.572B
Q8_026.8 GB~33.4–48.1 t/s~15170–31500 t/s128KComfortableEstimated
Mistral Small 3.2 24B
Mistral AI · 24.011B
Q8_027.2 GB~32.9–47.3 t/s~14890–30920 t/s128KComfortableEstimated
Hunyuan Hy3
Tencent · 298.786B (21B active)
Q8_0314.1 GB~32–46 t/s~4510–9370 t/s256KComfortableEstimated
DeepSeek-V3.2
DeepSeek · 685.397B (37B active)
Q4_K_M412.1 GB~31.8–45.8 t/s~2240–4660 t/s160KComfortableEstimated
Qwen3 235B-A22B
Alibaba Qwen · 235.094B (22B active)
Q8_0246.9 GB~30.6–44 t/s~4970–10320 t/s256KComfortableEstimated
GLM-5.3
Z.ai · 753.33B (40B active)
Q4_K_M452.9 GB~29.5–42.5 t/s~2060–4280 t/s1024KComfortableEstimated
MiniMax M3
MiniMax · 427.04B (23B active)
Q8_0445.9 GB~29.3–42.1 t/s~3610–7490 t/s1024KComfortableEstimated
Gemma 3 27B
Google DeepMind · 27.432B
Q8_033.4 GB~28.9–41.6 t/s~13030–27070 t/s128KComfortableEstimated
Qwen3.8 27B
Alibaba Qwen · 27.781B
Q8_031.9 GB~28.6–41.1 t/s~12870–26730 t/s256KComfortableEstimated
Qwen3.6 27B
Alibaba Qwen · 27.781B
Q8_031.9 GB~28.6–41.1 t/s~12870–26730 t/s256KComfortableEstimated
Gemma 4 31B
Google DeepMind · 31.273B
Q8_041.0 GB~25.5–36.6 t/s~11430–23740 t/s256KComfortableEstimated
Qwen3 32B
Alibaba Qwen · 32.762B
Q8_037.1 GB~24.3–35 t/s~10910–22660 t/s40KComfortableEstimated
DeepSeek-R1-Distill 32B
DeepSeek · 32.764B
Q8_037.1 GB~24.3–35 t/s~10910–22660 t/s128KComfortableEstimated
Llama 3.3 70B
Meta · 70.554B
Q8_076.8 GB~11.5–16.5 t/s~5070–10520 t/s128KComfortableEstimated
Rows in grey are estimates from our bandwidth model, not measurements — they are shown as a range and never as a precise figure. Use the “measured only” filter to see just the 0 pairings on this machine that a real benchmark backs.
Ownership economicsUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$1,182
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $1,082 more
Net cash at purchase
$90,082
Calculated VAT not reclaimable
Total over 5 years
$70,927
Calculated after tax, after resale
Cost per USD/1M tokens
$29.04
Calculated 40.7M tokens/month

The $100 comparison uses the Codex Pro 5x / Claude Max 5x plans. A fixed planning conversion is used for USD. This compares monthly spend only: subscriptions have usage limits, local hardware has different capabilities and constraints, and taxes or regional pricing may change the charged amount. Prices checked 7 September 2026.

Monthly breakdown

Depreciation
79,272 over 5 years, straight-line to a 10,810 residual
$1,321.20
Electricity
72.9 kWh/month at 0.140/kWh
$10.20
Cost of capital
4.0%/yr on 50,446 average capital employed
$168.15
Monthly cost before tax$1,499.55
Electricity tax shield
Running costs are deductible business expenses
−$2.14
First-year expensing
§179 (100.0%)
−$315.29
Monthly economic cost after tax$1,182.12

Three different numbers, deliberately

Cash cost
$90,082
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$1,321.20/month
$79,272 written down over 5 years to a $10,810 residual.
After-tax economic cost
$1,182.12/month
Depreciation plus running costs plus cost of capital, less the tax those deductions save. This is the figure to compare between machines.
Assumptions and sources (verified 2026-09-07)
VAT rate
0% Official spec
VAT recoverable
0% Official spec
Federal C-corporation estimate at the flat 21% rate. Pass-through entities should use the sole-proprietor estimate as a rougher proxy.
Effective deduction rate
21.00% Calculated
Headline marginal rate 21.00%.
Depreciation
5 years, straight-line Assumption
Residual value
$10,810 (12%) Assumption
Extrapolated.
Electricity
$0.140/kWh Assumption
Average power draw
414 W Calculated
Load 1350 W for 20% of powered hours, idle 180 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $18,917 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$168.15/month Assumption
Assumes the machine generates tokens 20% of its 176 powered hours per month. Cost per token scales inversely with this number — halve the utilisation and the cost per token doubles.
Federal planning estimate only, not tax advice. State and local income tax, sales/use tax and incentives are excluded. It assumes 100% business use, a Section 179 election, enough business income to use it, and that the full annual limit remains available.