MiniMax M3 on Mac Studio M5 Ultra 512 GB
427.04B (23B active) on 512 GB at 1,200 GB/s. Hardware details · Model details
CompatibilityComfortable
Fits
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
257.7 GB
Calculated of 435.2 GB usable — 59%
Max practical context
1M
Calculated model supports 1M
Memory budget at 8K context
Model weights ⓘ
248.3 GB Calculated
KV cache ⓘ
0.9 GB Calculated
Runtime overhead ⓘ
8.5 GB Estimated
Total required
257.7 GB Calculated
Usable memory ⓘ
435.2 GB Assumption
Headroom
177.5 GB Calculated
Highest-precision quantization that leaves headroom: uses 59% of usable memory at 8K context.
Unified memory: weights, KV cache and the OS share the same 512 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 427.04B parameters must be resident in memory even though only ~23B are active per token. Memory follows total parameters; speed follows active parameters.
PerformanceEstimated0/10
Decode (generation)
~49.4–71.1 t/s
Estimated calculated, not measured
Prefill (prompt)
~293–608 t/s
Estimated
TTFT at 8K
~13.5–28.1 s
Estimated time to first token
Power while generating
225 W
Measured 1.07 tokens/s per watt
These figures are estimated, not measured. Nobody has published a benchmark of MiniMax M3 on this machine that we know of, so we calculate throughput from memory bandwidth and active parameter count. Estimates are always shown as a range. Expand the working below to see exactly how the number was produced.
How the estimate is calculated
- Decode: reading 23.0B active parameters at 4.85 bits/weight takes 13.26 ms at 1200 GB/s x 88% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- Prefill: 240 TFLOPS (FP16) x 1.69 calibrated against measured prefill on this platform x 22% assumed model-FLOPs utilisation, divided by 2 x 99.1B parameters per token.
- Prefill uses 99.1B effective parameters, not the 23B 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.
This model at other quantizations on this machine
| Quantization | Weights | Total needed | Utilisation | Fit | Max context |
|---|---|---|---|---|---|
MLX 4-bit | 232.7 GB | 241.6 GB | 56% | Comfortable | 1M |
Q4_K_Mrecommended | 248.3 GB | 257.7 GB | 59% | Comfortable | 1M |
Q8_0 | 431.0 GB | 445.9 GB | 102% | Does not fit | 0 |
Cost of running MiniMax M3 on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$118
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $18 more
Net cash at purchase
$11,350
Calculated VAT not reclaimable
Total over 5 years
$7,102
Calculated after tax, after resale
Cost per USD/1M tokens
$15.51
Calculated 7.6M 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.
Monthly breakdown
| Depreciation 7,945 over 5 years, straight-line to a 3,405 residual | $132.41 |
| Electricity 9.9 kWh/month at 0.140/kWh | $1.38 |
| Cost of capital 4.0%/yr on 7,377 average capital employed | $24.59 |
| Monthly cost before tax | $158.39 |
| Electricity tax shield Running costs are deductible business expenses | −$0.29 |
| First-year expensing §179 (100.0%) | −$39.72 |
| Monthly economic cost after tax | $118.37 |
Three different numbers, deliberately
Cash cost
$11,350
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$132.41/month
$7,945 written down over 5 years to a $3,405 residual.
After-tax economic cost
$118.37/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
$3,405 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.140/kWh Assumption
Average power draw
56 W Calculated
Load 225 W for 20% of powered hours, idle 14 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $2,383 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$24.59/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
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
5.3 t/s
Calculated purchase price only
Decode per $100/month
50.9 t/s
Calculated after-tax ownership cost
Tokens per joule
1.07
Calculated same as tokens/s per watt
USD per 1M output tokens
$15.51
Calculated at 20% utilisation
Local versus hosted APIs
| Hosted model | USD/1M output | Break-even | API at your volume | Verdict | Comparison type |
|---|---|---|---|---|---|
| Qwen3.8 Flash Alibaba Cloud | $0.42 | 76.9M/mo | $12 | API cheaper | Different model |
| DeepSeek-V4 Flash DeepSeek | $0.66 | 48.9M/mo | $18 | API cheaper | Different model |
| DeepSeek-V4 Pro DeepSeek | $1.98 | 16.3M/mo | $55 | API cheaper | Different model |
| DeepSeek V4 Pro (Together) Together AI | $4.40 | 5.6M/mo | $162 | Local cheaper | Different model |
| GLM-5.3 Z.ai | $4.40 | 7.6M/mo | $119 | About equal | Different model |
| Claude Haiku 4.5 Anthropic | $5.00 | 9.1M/mo | $99 | API cheaper | Different 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 $118/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.
MiniMax M3 on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| Mac Studio M3 Ultra 512 GB | ~28–40.3 t/s | €9.199 | Comfortable |
Nearest alternatives to the Mac Studio M5 Ultra 512 GB
Page quality score (why this page is or is not indexed)
11/13 — indexed. Generated pages are gated so we do not ask a search engine to rank a page with nothing computed to say. The directive is emitted in the page head via the metadata API, not in the body, so it is authoritative.
- Has a memory-fit calculation (+3)
- Has a performance estimate (+2)
- Has a price (+2)
- Has an ownership economics calculation (+2)
- Has model quality benchmarks (+1)
- Well connected (12 internal links) (+1)