modelrigs

Mixtral 8x22B on Mac Studio M3 Ultra 96 GB

140.63B (39B active) on 96 GB at 819 GB/s. Hardware details · Model details

No calculated fit. Mixtral 8x22B does not fit under standard overhead assumptions at MLX 4-bit: the model calculates 81.7 GB required against 81.6 GB usable.
CompatibilityDoes not fit
Calculated fit
No
Calculated Requires more than 97% of usable memory. Needs a smaller quantization or more memory.
Smallest catalogued quantization
MLX 4-bit
Calculated mlx
Memory required
81.7 GB
Calculated of 81.6 GB usable — 100%
Max practical context
0
Calculated model supports 64K

Memory budget at 8K context

Model weights ⓘ
76.6 GB Calculated
KV cache ⓘ
1.8 GB Calculated
Runtime overhead ⓘ
3.3 GB Estimated
Total required
81.7 GB Calculated
Headroom ⓘ
-0.1 GB Calculated
No quantization in our catalogue fits this machine.
Unified memory: weights, KV cache and the OS share the same 96 GB pool. We assume 85% is addressable by the GPU, which matches a headless machine with the wired-memory limit raised.
Mixture of experts: all 140.63B parameters must be resident in memory even though only ~39B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended MLX 4-bit

Decode, prefill and TTFT below are estimates for MLX 4-bit. We do not have a comparable MLX 4-bit measurement on this machine.

Estimated decode
—
Estimated MLX 4-bit; calculated range
Estimated prefill
—
Estimated MLX 4-bit; calculated range
Estimated TTFT at 8K
—
Estimated MLX 4-bit; calculated range
Hardware load reference
—
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 39.0B active parameters at 4.50 bits/weight takes 37.82 ms at 819 GB/s x 71% 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
MLX 4-bitsmallest listed76.6 GB76.6 GB81.7 GB100%Does not fit0
Q4_K_M81.8 GB81.8 GB87.0 GB107%Does not fit0
Q5_K_M95.9 GB95.9 GB101.6 GB124%Does not fit0
Q8_0141.9 GB141.9 GB148.9 GB183%Does not fit0
BF16261.9 GB261.9 GB272.6 GB334%Does not fit0
Cost of running Mixtral 8x22B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$0
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $100 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$0
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
0.0 kWh/month at 0.140/kWh
$0.00
Monthly cost before tax$0.00
Electricity tax shield
Running costs are deductible business expenses
-$0.00
Monthly economic cost after tax$0.00

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
$0.00/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 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.000/kWh Assumption
Average power draw
0 W Calculated
Load — for 20% of powered hours, idle 0 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 8x22B on other hardware
HardwareDecodePriceFit
Nearest alternatives to the Mac Studio M3 Ultra 96 GB
Mixtral 8x22B on Mac Studio M3 Ultra 256 GB256 GBMixtral 8x22B on Mac Studio M3 Ultra 512 GB512 GBMixtral 8x22B on Mac Studio M2 Max 96 GB96 GBMixtral 8x22B on Mac Studio M5 Ultra 96 GB96 GBMixtral 8x22B on Mac Studio M1 Ultra 128 GB128 GB
Compare Mac Studio M3 Ultra 96 GB against Mac Studio M3 Ultra 256 GB →