modelrigs

Mixtral 8x7B on NVIDIA RTX 6000 Ada 48 GB

46.703B (13B active) on 48 GB at 960 GB/s. Hardware details · Model details

Yes. Mixtral 8x7B fits on NVIDIA RTX 6000 Ada 48 GB at the recommended Q5_K_M configuration, requiring approximately 34.8 GB at 8K context. Practical context capacity is 32K.
CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
Q5_K_M
Calculated gguf
Memory required
34.8 GB
Calculated of 44.2 GB usable — 79%
Max practical context
32K
Calculated model supports 32K

Memory budget at 8K context

Model weights ⓘ
31.9 GB Calculated
KV cache ⓘ
1.0 GB Calculated
Runtime overhead ⓘ
2.0 GB Estimated
Total required
34.8 GB Calculated
Headroom ⓘ
9.3 GB Calculated
Highest-precision quantization that leaves headroom: uses 79% of usable memory at 8K context.
Discrete GPU: 48 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 46.703B parameters must be resident in memory even though only ~13B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended Q5_K_M

Decode, prefill and TTFT below are estimates for Q5_K_M. We do not have a comparable Q5_K_M measurement on this machine.

Estimated decode
—
Estimated Q5_K_M; calculated range
Estimated prefill
—
Estimated Q5_K_M; calculated range
Estimated TTFT at 8K
—
Estimated Q5_K_M; calculated range
Hardware load reference
300 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
  1. Decode: reading 13.0B active parameters at 5.69 bits/weight takes 13.76 ms at 960 GB/s x 70% achieved efficiency.
  2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
  • MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
  • 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
QuantizationResidentDiskTotal neededUtilisationFitMax context
Q4_K_M27.2 GB27.2 GB30.0 GB68%Comfortable32K
Q5_K_Mrecommended31.9 GB31.9 GB34.8 GB79%Comfortable32K
Q8_047.1 GB47.1 GB50.6 GB114%Does not fit0
BF1687.0 GB87.0 GB91.6 GB207%Does not fit0
Cost of running Mixtral 8x7B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$2
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $98 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$104
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
15.6 kWh/month at 0.140/kWh
$2.19
Monthly cost before tax$2.19
Electricity tax shield
Running costs are deductible business expenses
−$0.46
Monthly economic cost after tax$1.73

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
$1.73/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
89 W Calculated
Load 300 W for 20% of powered hours, idle 36 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
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.
Mixtral 8x7B on other hardware
HardwareDecodePriceFit
Nearest alternatives to the NVIDIA RTX 6000 Ada 48 GB
Mixtral 8x7B on Dual used RTX 4090 workstation (48 GB)48 GBMixtral 8x7B on NVIDIA RTX A6000 48 GB48 GBMixtral 8x7B on NVIDIA A100 PCIe 40 GB40 GBMixtral 8x7B on Dual RTX 5090 workstation (2x 32 GB)64 GBMixtral 8x7B on NVIDIA RTX 5000 Ada 32 GB32 GB
Compare NVIDIA RTX 6000 Ada 48 GB against Dual used RTX 4090 workstation (48 GB) →