Nemotron 3.5 Lightning 30B-A3B on GeForce RTX 3090 Ti 24 GB
31.578B (3B active) on 24 GB at 1,008 GB/s. Hardware details · Model details
Marginal. Nemotron 3.5 Lightning 30B-A3B fits on GeForce RTX 3090 Ti 24 GB at the recommended
Q4_K_M configuration, requiring approximately 20.0 GB at 8K context. Practical context capacity is 192K.CompatibilityBorderline
Calculated fit
Yes
Calculated Uses 90-97% of usable memory. Likely to load but fragile under load or long context.
Recommended quantization
Q4_K_M
Calculated gguf
Memory required
20.0 GB
Calculated of 22.1 GB usable — 91%
Max practical context
192K
Calculated model supports 1M
Memory budget at 8K context
Model weights ⓘ
18.4 GB Calculated
KV cache ⓘ
0.1 GB Calculated
Runtime overhead ⓘ
1.6 GB Estimated
Total required
20.0 GB Calculated
Headroom ⓘ
2.1 GB Calculated
Only a borderline fit (91% of usable memory). Expect to run headless and keep the context short.
Discrete GPU: 24 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 31.578B parameters must be resident in memory even though only ~3B are active per token. Memory follows total parameters; speed follows active parameters.
Hybrid cache: token-growing KV memory is charged only to 6 attention blocks; 23 Mamba-2 blocks use fixed-size convolution and recurrent state instead.
Borderline fit. It may load, but you will have little room for a longer context, a second process, or a desktop session.
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
—
Estimated Q4_K_M; calculated range
Estimated prefill
—
Estimated Q4_K_M; calculated range
Estimated TTFT at 8K
—
Estimated Q4_K_M; calculated range
Hardware load reference
450 W
Official spec hardware TDP; not this model run
No throughput figures for this configuration. We do not estimate performance for a model that cannot load.
How the estimate is calculated
- Decode: reading 3.0B active parameters at 4.85 bits/weight takes 2.58 ms at 1008 GB/s x 70% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- Per-token overhead of 0.8 ms (kernel launches, attention bookkeeping, sampling) is significant here — this model is not purely bandwidth-bound on this hardware.
- MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
- With few active parameters on fast memory, fixed per-token overhead rather than bandwidth sets the ceiling. Real engines vary widely in how well they hide it.
- No FP16 compute figure for this hardware, so prefill cannot be estimated.
- 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_Mrecommended | 18.4 GB | 18.4 GB | 20.0 GB | 91% | Borderline | 192K |
Q5_K_M | 21.5 GB | 21.5 GB | 23.3 GB | 105% | Does not fit | 0 |
Q8_0 | 31.9 GB | 31.9 GB | 33.9 GB | 154% | Does not fit | 0 |
BF16 | 58.8 GB | 58.8 GB | 61.7 GB | 279% | Does not fit | 0 |
Cost of running Nemotron 3.5 Lightning 30B-A3B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$3
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $97 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$156
Calculated after tax, after resale
Cost per USD/1M tokens
—
Calculated
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.
Monthly breakdown
| Depreciation 0 over 5 years, straight-line to a 0 residual | $0.00 |
| Electricity 23.4 kWh/month at 0.140/kWh | $3.28 |
| Monthly cost before tax | $3.28 |
| Electricity tax shield Running costs are deductible business expenses | −$0.69 |
| Monthly economic cost after tax | $2.59 |
Three different numbers, deliberately
Cash cost
$0
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$0.00/month
$0 written down over 5 years to a $0 residual.
After-tax economic cost
$2.59/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
$0 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
133 W Calculated
Load 450 W for 20% of powered hours, idle 54 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $0 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
not applied 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
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.
Nemotron 3.5 Lightning 30B-A3B on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| NVIDIA DGX H200 (8x H200, 1,128 GB) | ~533–768 t/s | $359,430 * | Comfortable |
| RTX 5090 workstation (1x 32 GB) | ~319–459 t/s | $3,332 * | Comfortable |
| Quad RTX 5090 workstation (4x 32 GB) | ~315–454 t/s | $12,611 * | Comfortable |
| Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) | ~293–422 t/s | $58,553 * | Comfortable |
| Dual RTX 5090 workstation (2x 32 GB) | ~249–359 t/s | $5,854 * | Comfortable |
| Used RTX 4090 workstation (24 GB) | ~237–342 t/s | $2,071 * | Borderline |
Nearest alternatives to the GeForce RTX 3090 Ti 24 GB
Nemotron 3.5 Lightning 30B-A3B on NVIDIA RTX A5000 24 GB24 GBNemotron 3.5 Lightning 30B-A3B on NVIDIA Tesla P40 24 GB24 GBNemotron 3.5 Lightning 30B-A3B on RTX 3090 workstation (Ryzen 9 7950X, 64 GB)24 GBNemotron 3.5 Lightning 30B-A3B on Used RTX 4090 workstation (24 GB)24 GBNemotron 3.5 Lightning 30B-A3B on NVIDIA RTX 5000 Ada 32 GB32 GB
Compare GeForce RTX 3090 Ti 24 GB against NVIDIA RTX A5000 24 GB →
Compare GeForce RTX 3090 Ti 24 GB against NVIDIA RTX A5000 24 GB →