Quad RTX 5090 workstation (4x 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.

NVIDIAcomponent18 models fit0 measured
Memory
128 GB
Official spec GDDR7
Memory bandwidth
7,168 GB/s
Official spec ~79% achieved in practice
Specifications
CPU
AMD Threadripper 7960X Official spec
GPU
4× 4x GeForce RTX 5090 32 GB Official spec
Memory
128 GB GDDR7 Official spec
Memory bandwidth
7,168 GB/s Official spec source
Achieved bandwidth
~79% (5,675 GB/s) Assumption
FP16 compute
~838 TFLOPS Official spec
System RAM
256 GB Official spec
Architecture
Discrete GPU with dedicated VRAM Official spec
Nominal power
2600 W Official spec
Measured load power
2250 W Measured
Idle power
190 W Measured
Released
30 Jan 2025 Official spec
128 GB of GDDR7 at the cost of a 2.6 kW power budget that exceeds a standard Dutch 16 A wall circuit shared with anything else. Included as the upper bound of the GPU-workstation approach; the electricity line in the economics is not a rounding error here. Achieved-bandwidth coefficient INHERITED from rtx-5090-workstation, which shares the same silicon and software stack.
Model performance on Quad RTX 5090 workstation (4x 32 GB)0 measured, 18 estimated
18 of 18 rows
ModelQuantMemoryDecodePrefillContextFitConfidence
gpt-oss-20b
OpenAI · 20.915B (3.6B active)
MXFP414.2 GB~387–556 t/s~23090–47960 t/s128KComfortableEstimated
gpt-oss-120b
OpenAI · 116.829B (5.1B active)
MXFP467.7 GB~339–487 t/s~8210–17050 t/s128KComfortableEstimated
Qwen3.8 Flash Next
Alibaba Qwen · 180B (6B active)
MLX 4-bit104.0 GB~307–442 t/s~6100–12660 t/sBorderlineEstimated
Qwen3-Coder 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q8_034.7 GB~301–434 t/s~9980–20730 t/s256KComfortableEstimated
Qwen3 30B-A3B
Alibaba Qwen · 30.532B (3.3B active)
Q8_034.7 GB~301–434 t/s~9980–20730 t/s40KComfortableEstimated
Gemma 4 26B-A4B
Google DeepMind · 25.806B (3.8B active)
Q8_030.9 GB~281–404 t/s~10120–21010 t/s256KComfortableEstimated
Qwen3.5 122B-A10B
Alibaba Qwen · 125.086B (10B active)
Q4_K_M77.9 GB~223–320 t/s~2830–5880 t/s256KComfortableEstimated
Qwen3 8B
Alibaba Qwen · 8.191B
Q8_011.8 GB~196–282 t/s~12230–25400 t/s40KComfortableEstimated
Phi-4 14B
Microsoft · 14.66B
Q8_019.0 GB~128–185 t/s~6830–14190 t/s16KComfortableEstimated
Devstral Small 24B
Mistral AI · 23.572B
Q8_028.0 GB~87–125 t/s~4250–8830 t/s128KComfortableEstimated
Mistral Small 3.2 24B
Mistral AI · 24.011B
Q8_028.4 GB~85.7–123 t/s~4170–8670 t/s128KComfortableEstimated
Gemma 3 27B
Google DeepMind · 27.432B
Q8_034.6 GB~76.4–110 t/s~3650–7590 t/s128KComfortableEstimated
Qwen3.8 27B
Alibaba Qwen · 27.781B
Q8_033.1 GB~75.5–109 t/s~3610–7490 t/s256KComfortableEstimated
Qwen3.6 27B
Alibaba Qwen · 27.781B
Q8_033.1 GB~75.5–109 t/s~3610–7490 t/s256KComfortableEstimated
Gemma 4 31B
Google DeepMind · 31.273B
Q8_042.2 GB~68.1–98 t/s~3200–6650 t/s64KComfortableEstimated
Qwen3 32B
Alibaba Qwen · 32.762B
Q8_038.3 GB~65.3–94 t/s~3060–6350 t/s40KComfortableEstimated
DeepSeek-R1-Distill 32B
DeepSeek · 32.764B
Q8_038.3 GB~65.3–94 t/s~3060–6350 t/s128KComfortableEstimated
Llama 3.3 70B
Meta · 70.554B
Q8_078.0 GB~32.3–46.4 t/s~1420–2950 t/s64KComfortableEstimated
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
$170
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $70 more
Net cash at purchase
$12,611
Calculated VAT not reclaimable
Total over 5 years
$10,224
Calculated after tax, after resale
Cost per USD/1M tokens
$2.85
Calculated 59.8M 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
10,719 over 5 years, straight-line to a 1,892 residual
$178.65
Electricity
106.0 kWh/month at 0.140/kWh
$14.83
Cost of capital
4.0%/yr on 7,251 average capital employed
$24.17
Monthly cost before tax$217.65
Electricity tax shield
Running costs are deductible business expenses
−$3.11
First-year expensing
§179 (100.0%)
−$44.14
Monthly economic cost after tax$170.40

Three different numbers, deliberately

Cash cost
$12,611
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$178.65/month
$10,719 written down over 5 years to a $1,892 residual.
After-tax economic cost
$170.40/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
$1,892 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
602 W Calculated
Load 2250 W for 20% of powered hours, idle 190 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $2,648 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$24.17/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.