RTX 5090 workstation (1x 32 GB)

The fastest consumer memory subsystem you can buy: 1,792 GB/s of GDDR7. Only 32 GB of it, which is the whole story of this card for local AI — extremely fast on anything that fits, useless on anything that does not.

NVIDIAcomponent14 models fit2 measured
Memory
32 GB
Official spec GDDR7
Memory bandwidth
1,792 GB/s
Official spec ~79% achieved in practice
Specifications
CPU
AMD Ryzen 9 9950X Official spec
GPU
GeForce RTX 5090 32 GB Official spec
Memory
32 GB GDDR7 Official spec
Memory bandwidth
1,792 GB/s Official spec source
Achieved bandwidth
~79% (1,419 GB/s) Measured
FP16 compute
~210 TFLOPS Official spec
System RAM
64 GB Official spec
Architecture
Discrete GPU with dedicated VRAM Official spec
Nominal power
700 W Official spec
Measured load power
640 W Measured
Idle power
70 W Measured
Released
30 Jan 2025 Official spec
Complete system price: card at roughly EUR 2,400 street plus about EUR 1,300 of platform. 1,792 GB/s makes anything that fits in 32 GB extremely fast; nothing above 32 GB fits without a large speed penalty. Achieved-bandwidth coefficient CALIBRATED to 79% from 3 measured runs on this configuration.
Model performance on RTX 5090 workstation (1x 32 GB)2 measured, 12 estimated
14 of 14 rows
ModelQuantMemoryDecodePrefillContextFitConfidence
gpt-oss-20b
OpenAI · 20.915B (3.6B active)
MXFP413.0 GB419 t/s128KComfortableLow
Qwen3-Coder 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q4_K_M20.0 GB~333–480 t/s~3070–6380 t/s64KComfortableEstimated
Gemma 4 26B-A4B
Google DeepMind · 25.806B (3.8B active)
Q4_K_M18.3 GB~303–435 t/s~3110–6470 t/s32KComfortableEstimated
Qwen3 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q4_K_M20.0 GB352 t/s40KComfortableLow
Qwen3 8B
Alibaba Qwen · 8.191B
Q8_010.6 GB~118–170 t/s~3760–7820 t/s40KComfortableEstimated
Devstral Small 24B
Mistral AI · 23.572B
Q4_K_M16.4 GB~75.4–109 t/s~1310–2720 t/s64KComfortableEstimated
Mistral Small 3.2 24B
Mistral AI · 24.011B
Q4_K_M16.6 GB~74.1–107 t/s~1280–2670 t/s64KComfortableEstimated
Phi-4 14B
Microsoft · 14.66B
Q8_017.8 GB~69.6–100 t/s~2100–4370 t/s16KComfortableEstimated
Gemma 3 27B
Google DeepMind · 27.432B
Q4_K_M21.3 GB~65.5–94.2 t/s~1120–2330 t/s16KComfortableEstimated
Qwen3.8 27B
Alibaba Qwen · 27.781B
Q4_K_M19.6 GB~64.7–93.1 t/s~1110–2300 t/s32KComfortableEstimated
Qwen3.6 27B
Alibaba Qwen · 27.781B
Q4_K_M19.6 GB~64.7–93.1 t/s~1110–2300 t/s32KComfortableEstimated
Gemma 4 31B
Google DeepMind · 31.273B
MLX 4-bit26.0 GB~62.1–89.4 t/s~1970–4090 t/s8KFitsEstimated
Qwen3 32B
Alibaba Qwen · 32.762B
Q4_K_M22.6 GB~55.4–79.7 t/s~941–1950 t/s16KComfortableEstimated
DeepSeek-R1-Distill 32B
DeepSeek · 32.764B
Q4_K_M22.6 GB~55.4–79.7 t/s~941–1950 t/s16KComfortableEstimated
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 2 pairings on this machine that a real benchmark backs.
Ownership economicsUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$46
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $54 less
Net cash at purchase
$3,332
Calculated VAT not reclaimable
Total over 5 years
$2,731
Calculated after tax, after resale
Cost per USD/1M tokens
$0.86
Calculated 53.1M 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
2,832 over 5 years, straight-line to a 500 residual
$47.21
Electricity
32.4 kWh/month at 0.140/kWh
$4.53
Cost of capital
4.0%/yr on 1,916 average capital employed
$6.39
Monthly cost before tax$58.13
Electricity tax shield
Running costs are deductible business expenses
−$0.95
First-year expensing
§179 (100.0%)
−$11.66
Monthly economic cost after tax$45.51

Three different numbers, deliberately

Cash cost
$3,332
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$47.21/month
$2,832 written down over 5 years to a $500 residual.
After-tax economic cost
$45.51/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
$500 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
184 W Calculated
Load 640 W for 20% of powered hours, idle 70 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $700 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$6.39/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.