Phi-4 14B on Dual used RTX 4090 workstation (48 GB)
14.66B on 48 GB at 2,016 GB/s. Hardware details · Model details
Yes. Phi-4 14B fits on Dual used RTX 4090 workstation (48 GB) at the recommended
Q8_0 configuration, requiring approximately 18.2 GB at 8K context. Practical context capacity is 16K. Expected decode for the recommended configuration is ~52.7–75.9 t/s. EstimatedCompatibilityComfortable
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
18.2 GB
Calculated of 42.2 GB usable — 43%
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 ⓘ
1.8 GB Estimated
Total required
18.2 GB Calculated
Headroom ⓘ
24.0 GB Calculated
Highest-precision quantization that leaves headroom: uses 43% of usable memory at 8K context.
2 GPUs providing 48 GB aggregate VRAM. Assumes tensor- or layer-parallel sharding; each GPU carries its own context and communication buffers.
Multi-GPU throughput depends heavily on interconnect. Without NVLink or NVSwitch, tensor parallelism over PCIe adds latency that partially offsets the extra bandwidth.
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
~52.7–75.9 t/s
Estimated Q8_0; calculated range
Estimated prefill
~3800–7900 t/s
Estimated Q8_0; calculated range
Estimated TTFT at 8K
~1.1–2.3 s
Estimated Q8_0; calculated range
Hardware load reference
980 W
Measured machine-level load; not this model run
How the estimate is calculated
- Multi-GPU: 1008 GB/s per card, with each additional card contributing 40% of its bandwidth — 1411 GB/s effective, not the 2016 GB/s aggregate. Cross-GPU collectives use PCIe rather than a dedicated GPU fabric.
- Decode: reading 14.7B active parameters at 8.50 bits/weight takes 14.15 ms at 1411 GB/s x 78% achieved efficiency.
- Prefill: 330 TFLOPS (FP16) x 2 for native FP8 tensor cores x 26% 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
| Quantization | Resident | Disk | Total needed | Utilisation | Fit | Max context |
|---|---|---|---|---|---|---|
Q4_K_M | 8.5 GB | 8.5 GB | 11.7 GB | 28% | Comfortable | 16K |
Q5_K_M | 10.0 GB | 10.0 GB | 13.3 GB | 31% | Comfortable | 16K |
Q8_0recommended | 14.8 GB | 14.8 GB | 18.2 GB | 43% | Comfortable | 16K |
BF16 | 27.3 GB | 27.3 GB | 31.1 GB | 74% | Comfortable | 16K |
Cost of running Phi-4 14B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$48
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $52 less
Net cash at purchase
$3,692
Calculated VAT not reclaimable
Total over 5 years
$2,873
Calculated after tax, after resale
Cost per USD/1M tokens
$5.88
Calculated 8.1M 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.
Purchase-price input: $3,692 in United States (federal), tax/VAT excluded · estimated · Used market (Marktplaats/eBay) (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 2,880 over 5 years, straight-line to a 812 residual | $48.00 |
| Electricity 47.9 kWh/month at 0.140/kWh | $6.70 |
| Cost of capital 4.0%/yr on 2,252 average capital employed | $7.51 |
| Monthly cost before tax | $62.21 |
| Electricity tax shield Running costs are deductible business expenses | −$1.41 |
| First-year expensing §179 (100.0%) | −$12.92 |
| Monthly economic cost after tax | $47.88 |
Three different numbers, deliberately
Cash cost
$3,692
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$48.00/month
$2,880 written down over 5 years to a $812 residual.
After-tax economic cost
$47.88/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
$812 (22%) Assumption
Extrapolated.
Electricity
$0.140/kWh Assumption
Average power draw
272 W Calculated
Load 980 W for 20% of powered hours, idle 95 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $775 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$7.51/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.
Efficiency metrics
Decode per $1,000 spent
17.4 t/s
Calculated purchase price only
Decode per $100/month
134.3 t/s
Calculated after-tax ownership cost
Tokens per joule
0.24
Calculated same as tokens/s per watt
USD per 1M output tokens
$5.88
Calculated at 20% utilisation
Local versus hosted APIs
| Hosted model | USD/1M output | Break-even | API at your volume | Verdict | Comparison type |
|---|---|---|---|---|---|
| Qwen3.8 Flash Alibaba Cloud | $0.42 | 31.1M/mo | $13 | API cheaper | Different model |
| DeepSeek-V4.1 Flash DeepSeek | $0.60 | 26.6M/mo | $15 | API cheaper | Different model |
| DeepSeek-V4 Pro DeepSeek | $1.98 | 6.6M/mo | $59 | Local cheaper | Different model |
| DeepSeek V4 Pro (Together) Together AI | $4.40 | 2.3M/mo | $173 | Local cheaper | Different model |
| GLM-5.3 Z.ai | $4.40 | 3.1M/mo | $127 | Local cheaper | Different model |
| Claude Haiku 4.5 Anthropic | $5.00 | 3.7M/mo | $106 | Local cheaper | Different 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 $48/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
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| 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 5090 workstation (1x 32 GB) | ~69.6–100 t/s | $3,332 * | Comfortable |
Nearest alternatives to the Dual used RTX 4090 workstation (48 GB)
Phi-4 14B on Used RTX 4090 workstation (24 GB)24 GBPhi-4 14B on RTX 5090 workstation (1x 32 GB)32 GBPhi-4 14B on Dual RTX 5090 workstation (2x 32 GB)64 GBPhi-4 14B on NVIDIA RTX 6000 Ada 48 GB48 GBPhi-4 14B on NVIDIA RTX A6000 48 GB48 GB
Compare Dual used RTX 4090 workstation (48 GB) against Used RTX 4090 workstation (24 GB) →
Compare Dual used RTX 4090 workstation (48 GB) against Used RTX 4090 workstation (24 GB) →