CPU-only workstation (Ryzen 9950X, 192 GB DDR5)
A conventional desktop with a lot of cheap DDR5 and no GPU. Only viable for sparse MoE models, where the small active parameter count keeps the 90 GB/s of dual-channel bandwidth from being fatal. Included as the low-cost floor of the comparison.
GenericsystemAvailable24 models fit0 measured
Memory
192 GB
Official spec DDR5-5600 dual channel
Memory bandwidth
90 GB/s
Official spec ~50% achieved in practice
Specifications
CPU
AMD Ryzen 9 9950X, 16-core Official spec
GPU
None (integrated only) Official spec
Memory
192 GB DDR5-5600 dual channel Official spec
Memory bandwidth
90 GB/s Official spec source
Achieved bandwidth ⓘ
~50% (45 GB/s) Assumption
FP16 compute ⓘ
~4 TFLOPS Official spec
Architecture
Discrete GPU with dedicated VRAM Official spec
Nominal power
250 W Official spec
Measured load power
190 W Measured
Idle power
35 W Measured
Released
15 Aug 2024 Official spec
192 GB of capacity for EUR 1,699 and 90 GB/s of bandwidth. Only sensible for sparse MoE models where active parameters are small; a dense 70B model at 4-bit would run at roughly 1 token/second. Included so the configurator can show why capacity alone is not enough.
Standout models on this machine
Fastest
gpt-oss-20b — ~16.1–23.1 t/s
MXFP4 · estimated confidence
Largest that fits
Compare against
Related hardware
Quad RTX 5090 workstation (4x 32 GB)128 GB · 7,168 GB/sRTX 3090 workstation (Ryzen 9 7950X, 64 GB)24 GB · 936 GB/sUsed RTX 4090 workstation (24 GB)24 GB · 1,008 GB/sRadeon AI PRO R9700 workstation (32 GB)32 GB · 644 GB/sRTX PRO 6000 Blackwell workstation (96 GB)96 GB · 1,792 GB/sRTX PRO 6000 Max-Q workstation (96 GB, 300 W)96 GB · 1,792 GB/s
Model performance on CPU-only workstation (Ryzen 9950X, 192 GB DDR5)0 measured, 24 estimated
24 of 24 rows
| Model↕ | Quant | Memory↕ | Decode▼ | Prefill↕ | Context | Fit | Confidence↕ |
|---|---|---|---|---|---|---|---|
| gpt-oss-20b OpenAI · 20.915B (3.6B active) | MXFP4recommended | 13.0 GB | ~16.1–23.1 t/s | ~47.9–99.6 t/s | 128K | Comfortable | Estimated |
| gpt-oss-120b OpenAI · 116.829B (5.1B active) | MXFP4recommended | 66.5 GB | ~11.4–16.4 t/s | ~17–35.4 t/s | 128K | Comfortable | Estimated |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA · 31.578B (3B active) | Q8_0recommended | 33.9 GB | ~9.7–14 t/s | ~42.7–88.8 t/s | 1024K | Comfortable | Estimated |
| Qwen3-Coder 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 33.5 GB | ~8.8–12.7 t/s | ~41.4–86.1 t/s | 256K | Comfortable | Estimated |
| Qwen3 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 33.5 GB | ~8.8–12.7 t/s | ~41.4–86.1 t/s | 40K | Comfortable | Estimated |
| Gemma 4 26B-A4B Google DeepMind · 25.806B (3.8B active) | Q8_0recommended | 29.7 GB | ~7.7–11 t/s | ~42–87.2 t/s | 256K | Comfortable | Estimated |
| Qwen3.8 Flash Next Alibaba Qwen · 180B (6B active) | Q5_K_Mrecommended | 127.7 GB | ~7.3–10.5 t/s | ~12.7–26.3 t/s | 256K | Comfortable | Estimated |
| Step 3.7 Flash 198B-A11B StepFun · 201.365B (11B active) | Q4_K_Mrecommended | 132.9 GB | ~4.7–6.7 t/s | ~8.8–18.4 t/s | 32K | Comfortable | Estimated |
| Mistral Small 4 119B-A6.5B Mistral AI · 119.401B (6.5B active) | Q8_0recommended | 125.3 GB | ~4.5–6.5 t/s | ~14.9–31 t/s | 256K | Comfortable | Estimated |
| Qwen3 8B Alibaba Qwen · 8.191B | Q8_0recommended | 10.6 GB | ~4.2–6 t/s | ~50.8–105 t/s | 40K | Comfortable | Estimated |
| Qwen3.5 122B-A10B Alibaba Qwen · 125.086B (10B active) | Q8_0recommended | 131.2 GB | ~2.9–4.2 t/s | ~11.8–24.4 t/s | 256K | Comfortable | Estimated |
| Nemotron 3 Super 120B-A12B NVIDIA · 123.611B (12B active) | Q8_0recommended | 129.7 GB | ~2.4–3.5 t/s | ~10.8–22.4 t/s | 1024K | Comfortable | Estimated |
| Phi-4 14B Microsoft · 14.66B | Q8_0recommended | 17.8 GB | ~2.4–3.4 t/s | ~28.4–58.9 t/s | 16K | Comfortable | Estimated |
| Qwen3 235B-A22B Alibaba Qwen · 235.094B (22B active) | Q4_K_Mrecommended | 143.3 GB | ~2.3–3.4 t/s | ~5.8–12 t/s | 128K | Fits | Estimated |
| Devstral Small 24B Mistral AI · 23.572B | Q8_0recommended | 26.8 GB | ~1.5–2.1 t/s | ~17.6–36.7 t/s | 128K | Comfortable | Estimated |
| Mistral Small 3.2 24B Mistral AI · 24.011B | Q8_0recommended | 27.2 GB | ~1.4–2.1 t/s | ~17.3–36 t/s | 128K | Comfortable | Estimated |
| Gemma 3 27B Google DeepMind · 27.432B | Q8_0recommended | 33.4 GB | ~1.3–1.8 t/s | ~15.2–31.5 t/s | 128K | Comfortable | Estimated |
| Qwen3.8 27B Alibaba Qwen · 27.781B | Q8_0recommended | 30.4 GB | ~1.2–1.8 t/s | ~15–31.1 t/s | 256K | Comfortable | Estimated |
| Qwen3.6 27B Alibaba Qwen · 27.781B | Q8_0recommended | 30.4 GB | ~1.2–1.8 t/s | ~15–31.1 t/s | 256K | Comfortable | Estimated |
| Granite 4.2 30B IBM · 29.277B | Q8_0recommended | 33.4 GB | ~1.2–1.7 t/s | ~14.2–29.5 t/s | 128K | Comfortable | Estimated |
| Gemma 4 31B Google DeepMind · 31.273B | Q8_0recommended | 41.0 GB | ~1.1–1.6 t/s | ~13.3–27.6 t/s | 128K | Comfortable | Estimated |
| Qwen3 32B Alibaba Qwen · 32.762B | Q8_0recommended | 37.1 GB | ~1.1–1.5 t/s | ~12.7–26.4 t/s | 40K | Comfortable | Estimated |
| DeepSeek-R1-Distill 32B DeepSeek · 32.764B | Q8_0recommended | 37.1 GB | ~1.1–1.5 t/s | ~12.7–26.4 t/s | 128K | Comfortable | Estimated |
| Llama 3.3 70B Meta · 70.554B | Q8_0recommended | 76.8 GB | ~0.5–0.7 t/s | ~5.9–12.2 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
$21
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $79 less
Net cash at purchase
$1,531
Calculated VAT not reclaimable
Total over 5 years
$1,233
Calculated after tax, after resale
Cost per USD/1M tokens
$8.27
Calculated 2.5M 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: $1,531 in United States (federal), tax/VAT excluded · estimated · NL retail (system build) (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 1,301 over 5 years, straight-line to a 230 residual | $21.68 |
| Electricity 11.6 kWh/month at 0.140/kWh | $1.63 |
| Cost of capital 4.0%/yr on 880 average capital employed | $2.93 |
| Monthly cost before tax | $26.24 |
| Electricity tax shield Running costs are deductible business expenses | −$0.34 |
| First-year expensing §179 (100.0%) | −$5.36 |
| Monthly economic cost after tax | $20.54 |
Three different numbers, deliberately
Cash cost
$1,531
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$21.68/month
$1,301 written down over 5 years to a $230 residual.
After-tax economic cost
$20.54/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
$230 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
66 W Calculated
Load 190 W for 20% of powered hours, idle 35 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $321 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$2.93/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.