Phi-3.5 MoE 42B-A6.6B on RTX PRO 6000 Max-Q workstation (96 GB, 300 W)
41.873B (6.6B active) on 96 GB at 1,792 GB/s. Hardware details · Model details
Yes. Phi-3.5 MoE 42B-A6.6B fits on RTX PRO 6000 Max-Q workstation (96 GB, 300 W) at the recommended
Q8_0 configuration, requiring approximately 45.5 GB at 8K context. Practical context capacity is 128K.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
45.5 GB
Calculated of 88.3 GB usable — 52%
Max practical context
128K
Calculated model supports 128K
Memory budget at 8K context
Model weights ⓘ
42.3 GB Calculated
KV cache ⓘ
1.0 GB Calculated
Runtime overhead ⓘ
2.3 GB Estimated
Total required
45.5 GB Calculated
Headroom ⓘ
42.8 GB Calculated
Highest-precision quantization that leaves headroom: uses 52% of usable memory at 8K context.
Discrete GPU: 96 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 41.873B parameters must be resident in memory even though only ~6.6B are active per token. Memory follows total parameters; speed follows active parameters.
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
—
Estimated Q8_0; calculated range
Estimated prefill
—
Estimated Q8_0; calculated range
Estimated TTFT at 8K
~2.5–5.2 s
Estimated Q8_0; calculated range
Hardware load reference
390 W
Measured machine-level load; 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 6.6B active parameters at 8.50 bits/weight takes 5.27 ms at 1792 GB/s x 74% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- Prefill: 190 TFLOPS (FP16) x 2 for native FP8 tensor cores x 0.67 calibrated against measured prefill on this platform x 32% assumed model-FLOPs utilisation, divided by 2 x 16.6B parameters per token.
- Prefill uses 16.6B effective parameters, not the 6.6B active in decode: a batch of hundreds of tokens routes across most of the expert pool.
- MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
- 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 | 24.4 GB | 24.4 GB | 27.1 GB | 31% | Comfortable | 128K |
Q5_K_M | 28.6 GB | 28.6 GB | 31.4 GB | 36% | Comfortable | 128K |
Q8_0recommended | 42.3 GB | 42.3 GB | 45.5 GB | 52% | Comfortable | 128K |
BF16 | 78.0 GB | 78.0 GB | 82.3 GB | 93% | Borderline | 32K |
Cost of running Phi-3.5 MoE 42B-A6.6B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$138
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $38 more
Net cash at purchase
$10,809
Calculated VAT not reclaimable
Total over 5 years
$8,294
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.
Purchase-price input: $10,809 in United States (federal), tax/VAT excluded · estimated · NL workstation integrator (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 9,188 over 5 years, straight-line to a 1,621 residual | $153.13 |
| Electricity 20.1 kWh/month at 0.140/kWh | $2.81 |
| Cost of capital 4.0%/yr on 6,215 average capital employed | $20.72 |
| Monthly cost before tax | $176.65 |
| Electricity tax shield Running costs are deductible business expenses | −$0.59 |
| First-year expensing §179 (100.0%) | −$37.83 |
| Monthly economic cost after tax | $138.23 |
Three different numbers, deliberately
Cash cost
$10,809
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$153.13/month
$9,188 written down over 5 years to a $1,621 residual.
After-tax economic cost
$138.23/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
$1,621 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
114 W Calculated
Load 390 W for 20% of powered hours, idle 45 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $2,270 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$20.72/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
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.
Phi-3.5 MoE 42B-A6.6B on other hardware
| Hardware | Decode | Price | Fit |
|---|
Nearest alternatives to the RTX PRO 6000 Max-Q workstation (96 GB, 300 W)
Phi-3.5 MoE 42B-A6.6B on RTX PRO 6000 Blackwell workstation (96 GB)96 GBPhi-3.5 MoE 42B-A6.6B on Quad RTX 5090 workstation (4x 32 GB)128 GBPhi-3.5 MoE 42B-A6.6B on Dual RTX 5090 workstation (2x 32 GB)64 GBPhi-3.5 MoE 42B-A6.6B on Dual used RTX 4090 workstation (48 GB)48 GBPhi-3.5 MoE 42B-A6.6B on RTX 5090 workstation (1x 32 GB)32 GB
Compare RTX PRO 6000 Max-Q workstation (96 GB, 300 W) against RTX PRO 6000 Blackwell workstation (96 GB) →
Compare RTX PRO 6000 Max-Q workstation (96 GB, 300 W) against RTX PRO 6000 Blackwell workstation (96 GB) →