modelrigs

Phi-4 14B on RTX 5090 workstation (1x 32 GB)

14.66B on 32 GB at 1,792 GB/s. Hardware details · Model details

Run locally →
Yes. Phi-4 14B fits on RTX 5090 workstation (1x 32 GB) at the recommended Q8_0 configuration, requiring approximately 17.8 GB at 8K context. Practical context capacity is 16K. Expected decode for the recommended configuration is ~69.6–100 t/s. Estimated
CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
Q8_0
Calculated gguf
Memory required
17.8 GB
Calculated of 29.4 GB usable — 60%
Max practical context
16K
Calculated model supports 16K

Memory budget at 8K context

Model weights ⓘ
14.8 GB Calculated
KV cache ⓘ
1.6 GB Calculated
Runtime overhead ⓘ
1.4 GB Estimated
Total required
17.8 GB Calculated
Headroom ⓘ
11.6 GB Calculated
Highest-precision quantization that leaves headroom: uses 60% of usable memory at 8K context.
Discrete GPU: 32 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Performance

Estimated performance · recommended Q8_0

Decode, prefill and TTFT below are estimates for Q8_0. We do not have a comparable Q8_0 measurement on this machine.

Estimated decode
~69.6–100 t/s
Estimated Q8_0; calculated range
Estimated prefill
~2100–4370 t/s
Estimated Q8_0; calculated range
Estimated TTFT at 8K
~1.9–4.0 s
Estimated Q8_0; calculated range
Hardware load reference
640 W
Measured machine-level load; not this model run
How the estimate is calculated
  1. Decode: reading 14.7B active parameters at 8.50 bits/weight takes 10.98 ms at 1792 GB/s x 79% achieved efficiency.
  2. Prefill: 210 TFLOPS (FP16) x 2 for native FP8 tensor cores x 0.71 calibrated against measured prefill on this platform x 32% assumed model-FLOPs utilisation, divided by 2 x 14.7B parameters per token.
  • Prefill throughput is highly engine-dependent. Flash attention, batch size and quantized KV all move this number substantially, and for sparse mixture-of-experts models it is the least reliable figure we produce.
  • This is a calculated estimate, not a measurement. It assumes a single request, a short prompt, no speculative decoding and a warm model already resident in memory.

Estimator version estimator_v1. Stored with every estimated row so old estimates can be regenerated when the model improves.

Submit a benchmarkSubmissions stay pending until reviewed.
This model at other quantizations on this machine
QuantizationResidentDiskTotal neededUtilisationFitMax context
Q4_K_M8.5 GB8.5 GB11.3 GB39%Comfortable16K
Q5_K_M10.0 GB10.0 GB12.9 GB44%Comfortable16K
Q8_0recommended14.8 GB14.8 GB17.8 GB60%Comfortable16K
BF1627.3 GB27.3 GB30.7 GB104%Does not fit0
Cost of running Phi-4 14B on this machineUnited 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
$4.23
Calculated 10.8M 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.

Purchase-price input: $3,332 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
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.
Efficiency metrics
Decode per $1,000 spent
25.5 t/s
Calculated purchase price only
Decode per $100/month
186.5 t/s
Calculated after-tax ownership cost
Tokens per joule
0.46
Calculated same as tokens/s per watt
USD per 1M output tokens
$4.23
Calculated at 20% utilisation
Local versus hosted APIs
Hosted modelUSD/1M outputBreak-evenAPI at your volumeVerdictComparison type
Qwen3.8 Flash
Alibaba Cloud
$0.4229.6M/mo$17API cheaperDifferent model
DeepSeek-V4.1 Flash
DeepSeek
$0.6025.3M/mo$19API cheaperDifferent model
DeepSeek-V4 Pro
DeepSeek
$1.986.3M/mo$78Local cheaperDifferent model
DeepSeek V4 Pro (Together)
Together AI
$4.402.1M/mo$228Local cheaperDifferent model
GLM-5.3
Z.ai
$4.402.9M/mo$168Local cheaperDifferent model
Claude Haiku 4.5
Anthropic
$5.003.5M/mo$140Local cheaperDifferent model
Different-model comparison: the hosted model is not the model you would run locally. Treat this as a workload-quality trade-off, not a direct economic equivalence — the frontier model may complete a task in fewer tokens, or complete tasks the local model cannot. Break-even is the monthly output volume at which API spend equals the $46/month economic cost of owning this machine, assuming 8 input tokens per output token. Hosted prices are published in USD. This table is the canonical US default.
Phi-4 14B on other hardware
HardwareDecodePriceFit
NVIDIA DGX H200 (8x H200, 1,128 GB)~416–599 t/s$359,430 *Comfortable
Quad RTX 5090 workstation (4x 32 GB)~128–185 t/s$12,611 *Comfortable
Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)~114–164 t/s$58,553 *Comfortable
Dual RTX 5090 workstation (2x 32 GB)~88.7–128 t/s$5,854 *Comfortable
Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB)~81.8–118 t/s$36,663 *Comfortable
RTX PRO 6000 Blackwell workstation (96 GB)~65.6–94.4 t/s$10,359 *Comfortable
Nearest alternatives to the RTX 5090 workstation (1x 32 GB)
Phi-4 14B on Dual RTX 5090 workstation (2x 32 GB)64 GBPhi-4 14B on Quad RTX 5090 workstation (4x 32 GB)128 GBPhi-4 14B on Dual used RTX 4090 workstation (48 GB)48 GBPhi-4 14B on Used RTX 4090 workstation (24 GB)24 GBPhi-4 14B on RTX 3090 workstation (Ryzen 9 7950X, 64 GB)24 GB
Compare RTX 5090 workstation (1x 32 GB) against Dual RTX 5090 workstation (2x 32 GB) →