Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)
Lenovo's densest deskside AI workstation supports four 300 W RTX PRO 6000 Blackwell Max-Q cards. The resulting 384 GB of ECC VRAM is enough for many 300B-class models at high precision, while remaining a workstation rather than data-centre infrastructure.
LenovosystemAvailable29 models fit0 measured
Memory
384 GB
Official spec GDDR7 ECC (distributed)
Aggregate theoretical bandwidth
7,168 GB/s
Official spec raw sum; usable scaling is modelled separately
Specifications
CPU
Dual Intel Xeon Scalable Official spec
GPU
4× 4x NVIDIA RTX PRO 6000 Blackwell Max-Q 96 GB Official spec
Memory
384 GB GDDR7 ECC (distributed) Official spec
Aggregate theoretical bandwidth
7,168 GB/s raw sum Official spec source
Multi-GPU scaling ⓘ
Interconnect-adjusted in estimator Assumption
FP16 compute ⓘ
~760 TFLOPS Official spec
System RAM
512 GB Official spec
Interconnect
PCIe 5.0 x16 Official spec
Architecture
multi_gpu Official spec
Nominal power
2000 W Official spec
Measured load power
1580 W Measured
Idle power
210 W Measured
Released
1 Apr 2025 Official spec
Lenovo officially supports four RTX PRO 6000 Blackwell Max-Q cards for 384 GB aggregate VRAM. Price and whole-system power are ESTIMATES for a suitably configured Dutch system. The four cards have no pooled-memory fabric, so supported inference engines must shard weights over PCIe.
Standout models on this machine
Fastest
gpt-oss-20b — ~366–527 t/s
MXFP4 · estimated confidence
Largest that fits
Related hardware
Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB)192 GB · 3,584 GB/sNVIDIA DGX H200 (8x H200, 1,128 GB)1,128 GB · 38,400 GB/sNVIDIA DGX Station GB300 (748 GB)748 GB · 7,100 GB/sMac Studio M5 Ultra 512 GB512 GB · 1,200 GB/sMac Studio M3 Ultra 512 GB512 GB · 819 GB/sMac Studio M5 Ultra 256 GB256 GB · 1,200 GB/s
Model performance on Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)0 measured, 29 estimated
29 of 29 rows
| Model↕ | Quant | Memory↕ | Decode▼ | Prefill↕ | Context | Fit | Confidence↕ |
|---|---|---|---|---|---|---|---|
| gpt-oss-20b OpenAI · 20.915B (3.6B active) | MXFP4recommended | 14.2 GB | ~366–527 t/s | ~29600–61490 t/s | 128K | Comfortable | Estimated |
| gpt-oss-120b OpenAI · 116.829B (5.1B active) | MXFP4recommended | 67.7 GB | ~317–456 t/s | ~10520–21860 t/s | 128K | Comfortable | Estimated |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA · 31.578B (3B active) | Q8_0recommended | 35.1 GB | ~293–422 t/s | ~13200–27410 t/s | 1024K | Comfortable | Estimated |
| Qwen3-Coder 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 34.7 GB | ~279–402 t/s | ~12800–26580 t/s | 256K | Comfortable | Estimated |
| Qwen3 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 34.7 GB | ~279–402 t/s | ~12800–26580 t/s | 40K | Comfortable | Estimated |
| Gemma 4 26B-A4B Google DeepMind · 25.806B (3.8B active) | Q8_0recommended | 30.9 GB | ~259–372 t/s | ~12970–26940 t/s | 256K | Comfortable | Estimated |
| Qwen3.8 Flash Next Alibaba Qwen · 180B (6B active) | Q8_0recommended | 189.5 GB | ~195–281 t/s | ~3910–8120 t/s | 256K | Comfortable | Estimated |
| Mistral Small 4 119B-A6.5B Mistral AI · 119.401B (6.5B active) | Q8_0recommended | 126.5 GB | ~185–266 t/s | ~4610–9580 t/s | 256K | Comfortable | Estimated |
| Qwen3 8B Alibaba Qwen · 8.191B | Q8_0recommended | 11.8 GB | ~176–254 t/s | ~15680–32570 t/s | 40K | Comfortable | Estimated |
| DeepSeek-V4 Flash DeepSeek · 304.18B (13B active) | Q5_K_Mrecommended | 216.6 GB | ~150–216 t/s | ~2040–4240 t/s | 1024K | Comfortable | Estimated |
| Qwen3.5 122B-A10B Alibaba Qwen · 125.086B (10B active) | Q8_0recommended | 132.4 GB | ~135–195 t/s | ~3630–7540 t/s | 256K | Comfortable | Estimated |
| MiMo-V2.5 310B-A15B XiaomiMiMo · 310.756B (15B active) | Q5_K_Mrecommended | 221.7 GB | ~135–194 t/s | ~1880–3910 t/s | 512K | Comfortable | Estimated |
| Step 3.7 Flash 198B-A11B StepFun · 201.365B (11B active) | Q8_0recommended | 222.8 GB | ~126–181 t/s | ~2730–5670 t/s | 64K | Comfortable | Estimated |
| Nemotron 3 Super 120B-A12B NVIDIA · 123.611B (12B active) | Q8_0recommended | 130.9 GB | ~117–169 t/s | ~3330–6930 t/s | 1024K | Comfortable | Estimated |
| GLM-5.3 Flash Z.ai · 321.323B (18B active) | Q5_K_Mrecommended | 228.4 GB | ~117–168 t/s | ~1690–3510 t/s | 1024K | Comfortable | Estimated |
| Phi-4 14B Microsoft · 14.66B | Q8_0recommended | 19.0 GB | ~114–164 t/s | ~8760–18200 t/s | 16K | Comfortable | Estimated |
| MiniMax M3 MiniMax · 427.04B (23B active) | Q4_K_Mrecommended | 258.9 GB | ~109–157 t/s | ~1300–2690 t/s | 512K | Comfortable | Estimated |
| Hunyuan Hy3 Tencent · 298.786B (21B active) | Q5_K_Mrecommended | 214.7 GB | ~103–148 t/s | ~1620–3370 t/s | 256K | Comfortable | Estimated |
| Devstral Small 24B Mistral AI · 23.572B | Q8_0recommended | 28.0 GB | ~76.3–110 t/s | ~5450–11320 t/s | 128K | Comfortable | Estimated |
| Mistral Small 3.2 24B Mistral AI · 24.011B | Q8_0recommended | 28.4 GB | ~75.1–108 t/s | ~5350–11110 t/s | 128K | Comfortable | Estimated |
| Qwen3 235B-A22B Alibaba Qwen · 235.094B (22B active) | Q8_0recommended | 248.1 GB | ~70.3–101 t/s | ~1790–3710 t/s | 256K | Comfortable | Estimated |
| Gemma 3 27B Google DeepMind · 27.432B | Q8_0recommended | 34.6 GB | ~66.8–96.2 t/s | ~4680–9720 t/s | 128K | Comfortable | Estimated |
| Qwen3.8 27B Alibaba Qwen · 27.781B | Q8_0recommended | 31.6 GB | ~66.1–95.1 t/s | ~4620–9600 t/s | 256K | Comfortable | Estimated |
| Qwen3.6 27B Alibaba Qwen · 27.781B | Q8_0recommended | 31.6 GB | ~66.1–95.1 t/s | ~4620–9600 t/s | 256K | Comfortable | Estimated |
| Granite 4.2 30B IBM · 29.277B | Q8_0recommended | 34.6 GB | ~63.1–90.7 t/s | ~4390–9110 t/s | 128K | Comfortable | Estimated |
| Gemma 4 31B Google DeepMind · 31.273B | Q8_0recommended | 42.2 GB | ~59.4–85.5 t/s | ~4110–8530 t/s | 256K | Comfortable | Estimated |
| Qwen3 32B Alibaba Qwen · 32.762B | Q8_0recommended | 38.3 GB | ~57–82 t/s | ~3920–8140 t/s | 40K | Comfortable | Estimated |
| DeepSeek-R1-Distill 32B DeepSeek · 32.764B | Q8_0recommended | 38.3 GB | ~57–82 t/s | ~3920–8140 t/s | 128K | Comfortable | Estimated |
| Llama 3.3 70B Meta · 70.554B | Q8_0recommended | 78.0 GB | ~27.9–40.2 t/s | ~1820–3780 t/s | 128K | Comfortable | Estimated |
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.
Submit a benchmarkContributions are reviewed before publication.
Ownership economicsUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$746
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $646 more
Net cash at purchase
$58,553
Calculated VAT not reclaimable
Total over 5 years
$44,773
Calculated after tax, after resale
Cost per USD/1M tokens
$13.19
Calculated 56.6M 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.
Purchase-price input: $58,553 in United States (federal), tax/VAT excluded · estimated · Lenovo enterprise channel (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 49,770 over 5 years, straight-line to a 8,783 residual | $829.50 |
| Electricity 85.2 kWh/month at 0.140/kWh | $11.93 |
| Cost of capital 4.0%/yr on 33,668 average capital employed | $112.23 |
| Monthly cost before tax | $953.65 |
| Electricity tax shield Running costs are deductible business expenses | −$2.50 |
| First-year expensing §179 (100.0%) | −$204.93 |
| Monthly economic cost after tax | $746.21 |
Three different numbers, deliberately
Cash cost
$58,553
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$829.50/month
$49,770 written down over 5 years to a $8,783 residual.
After-tax economic cost
$746.21/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
$8,783 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
484 W Calculated
Load 1580 W for 20% of powered hours, idle 210 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $12,296 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$112.23/month Assumption
- VAT rate: No US federal VAT · verified 2026-09-07
- Marginal tax rate: IRS Publication 542 — Corporations · verified 2026-09-07
- VAT recoverable fraction: site assumption · verified 2026-09-07
- Useful life: IRS Publication 946 — How To Depreciate Property · verified 2026-09-07
- Electricity price: Site assumption · verified 2026-09-07
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.