modelrigs

Granite 4.2 30B on RTX 5090 workstation (1x 32 GB)

29.277B on 32 GB at 1,792 GB/s. Hardware details · Model details

Run locally →
Yes. Granite 4.2 30B fits on RTX 5090 workstation (1x 32 GB) at the recommended Q4_K_M configuration, requiring approximately 20.5 GB at 8K context. Practical context capacity is 32K. Expected decode for the recommended configuration is ~61.6–88.7 t/s. Estimated
CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
Q4_K_M
Calculated gguf
Memory required
20.5 GB
Calculated of 29.4 GB usable — 70%
Max practical context
32K
Calculated model supports 128K

Memory budget at 8K context

Model weights ⓘ
17.0 GB Calculated
KV cache ⓘ
2.0 GB Calculated
Runtime overhead ⓘ
1.5 GB Estimated
Total required
20.5 GB Calculated
Headroom ⓘ
8.9 GB Calculated
Highest-precision quantization that leaves headroom: uses 70% 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 Q4_K_M

Decode, prefill and TTFT below are estimates for Q4_K_M. We do not have a comparable Q4_K_M measurement on this machine.

Estimated decode
~61.6–88.7 t/s
Estimated Q4_K_M; calculated range
Estimated prefill
~1050–2190 t/s
Estimated Q4_K_M; calculated range
Estimated TTFT at 8K
~3.8–7.9 s
Estimated Q4_K_M; calculated range
Hardware load reference
640 W
Measured machine-level load; not this model run
How the estimate is calculated
  1. Decode: reading 29.3B active parameters at 4.85 bits/weight takes 12.51 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 29.3B 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_Mrecommended17.0 GB17.0 GB20.5 GB70%Comfortable32K
Q5_K_M20.0 GB20.0 GB23.6 GB80%Fits16K
Q8_029.5 GB29.5 GB33.4 GB114%Does not fit0
BF1654.5 GB54.5 GB59.2 GB201%Does not fit0
Cost of running Granite 4.2 30B 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
$4.78
Calculated 9.5M 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: $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
22.5 t/s
Calculated purchase price only
Decode per $100/month
165.1 t/s
Calculated after-tax ownership cost
Tokens per joule
0.41
Calculated same as tokens/s per watt
USD per 1M output tokens
$4.78
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$15API cheaperDifferent model
DeepSeek-V4.1 Flash
DeepSeek
$0.6025.3M/mo$17API cheaperDifferent model
DeepSeek-V4 Pro
DeepSeek
$1.986.3M/mo$69Local cheaperDifferent model
DeepSeek V4 Pro (Together)
Together AI
$4.402.1M/mo$202Local cheaperDifferent model
GLM-5.3
Z.ai
$4.402.9M/mo$149Local cheaperDifferent model
Claude Haiku 4.5
Anthropic
$5.003.5M/mo$124Local 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.
Granite 4.2 30B on other hardware
HardwareDecodePriceFit
NVIDIA DGX H200 (8x H200, 1,128 GB)~323–465 t/s$359,430 *Comfortable
Quad RTX 5090 workstation (4x 32 GB)~72.1–104 t/s$12,611 *Comfortable
Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)~63.1–90.7 t/s$58,553 *Comfortable
Dual RTX 5090 workstation (2x 32 GB)~48.1–69.2 t/s$5,854 *Comfortable
Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB)~44–63.4 t/s$36,663 *Comfortable
Dual used RTX 4090 workstation (48 GB)~40.4–58.1 t/s$3,692 *Comfortable
Nearest alternatives to the RTX 5090 workstation (1x 32 GB)
Granite 4.2 30B on Dual RTX 5090 workstation (2x 32 GB)64 GBGranite 4.2 30B on Quad RTX 5090 workstation (4x 32 GB)128 GBGranite 4.2 30B on Dual used RTX 4090 workstation (48 GB)48 GBGranite 4.2 30B on Used RTX 4090 workstation (24 GB)24 GBGranite 4.2 30B 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) →