Mac Studio M5 Max 128 GB
Apple's 2026 desktop workstation. The M5 generation adds Neural Accelerators to every GPU core, which lifts prefill throughput dramatically over M4; for bandwidth-bound decode, achieved memory bandwidth remains one of the strongest predictors once the model fits. Its combination of very large unified memory and low idle power makes it a strong option for running large MoE models at home.
ApplesystemAvailable22 models fit0 measured
Memory
128 GB
Official spec LPDDR5X unified
Memory bandwidth
614 GB/s
Official spec ~88% achieved in practice
Specifications
CPU
Apple M5 Max, 18-core Official spec
GPU
40-core GPU with Neural Accelerators Official spec
Memory
128 GB LPDDR5X unified Official spec
Memory bandwidth
614 GB/s Official spec source
Achieved bandwidth ⓘ
~88% (538 GB/s) Assumption
FP16 compute ⓘ
~120 TFLOPS Estimated
Architecture
Unified memory (CPU and GPU share one pool) Official spec
Nominal power
175 W Official spec
Measured load power
122 W Measured
Idle power
8 W Measured
Released
22 Sept 2026 Official spec
Maximum memory for the M5 Max. The sweet spot for 100B-class MoE models at 4-bit, at roughly half the price of an Ultra. Price is ESTIMATED from Apple's memory upgrade convention of roughly EUR 14/GB. Achieved-bandwidth coefficient CALIBRATED to 88% from 2 measured runs on this configuration.
Standout models on this machine
Fastest
gpt-oss-20b — ~158–228 t/s
MXFP4 · estimated confidence
Largest that fits
Compare against
Related hardware
Model performance on Mac Studio M5 Max 128 GB0 measured, 22 estimated
22 of 22 rows
| Model↕ | Quant | Memory↕ | Decode▼ | Prefill↕ | Context | Fit | Confidence↕ |
|---|---|---|---|---|---|---|---|
| gpt-oss-20b OpenAI · 20.915B (3.6B active) | MXFP4recommended | 13.0 GB | ~158–228 t/s | ~1670–3470 t/s | 128K | Comfortable | Estimated |
| gpt-oss-120b OpenAI · 116.829B (5.1B active) | MXFP4recommended | 66.5 GB | ~118–170 t/s | ~594–1230 t/s | 128K | Comfortable | Estimated |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA · 31.578B (3B active) | Q8_0recommended | 33.9 GB | ~103–148 t/s | ~1490–3100 t/s | 1024K | Comfortable | Estimated |
| Qwen3.8 Flash Next Alibaba Qwen · 180B (6B active) | MLX 4-bitrecommended | 102.2 GB | ~97.9–141 t/s | ~442–917 t/s | 128K | Borderline | Estimated |
| Qwen3-Coder 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 33.5 GB | ~94.6–136 t/s | ~1450–3000 t/s | 256K | Comfortable | Estimated |
| Qwen3 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q8_0recommended | 33.5 GB | ~94.6–136 t/s | ~1450–3000 t/s | 40K | Comfortable | Estimated |
| Gemma 4 26B-A4B Google DeepMind · 25.806B (3.8B active) | Q8_0recommended | 29.7 GB | ~83.4–120 t/s | ~1470–3040 t/s | 256K | Comfortable | Estimated |
| Mistral Small 4 119B-A6.5B Mistral AI · 119.401B (6.5B active) | Q5_K_Mrecommended | 85.1 GB | ~73.8–106 t/s | ~521–1080 t/s | 256K | Comfortable | Estimated |
| Qwen3.5 122B-A10B Alibaba Qwen · 125.086B (10B active) | Q4_K_Mrecommended | 76.1 GB | ~57.5–82.8 t/s | ~410–852 t/s | 256K | Comfortable | Estimated |
| Nemotron 3 Super 120B-A12B NVIDIA · 123.611B (12B active) | Q4_K_Mrecommended | 75.3 GB | ~48.5–69.8 t/s | ~377–783 t/s | 1024K | Comfortable | Estimated |
| Qwen3 8B Alibaba Qwen · 8.191B | Q8_0recommended | 10.6 GB | ~47.7–68.7 t/s | ~1770–3680 t/s | 40K | Comfortable | Estimated |
| Phi-4 14B Microsoft · 14.66B | Q8_0recommended | 17.8 GB | ~27.4–39.4 t/s | ~990–2060 t/s | 16K | Comfortable | Estimated |
| Devstral Small 24B Mistral AI · 23.572B | Q8_0recommended | 26.8 GB | ~17.2–24.8 t/s | ~616–1280 t/s | 128K | Comfortable | Estimated |
| Mistral Small 3.2 24B Mistral AI · 24.011B | Q8_0recommended | 27.2 GB | ~16.9–24.4 t/s | ~604–1260 t/s | 128K | Comfortable | Estimated |
| Gemma 3 27B Google DeepMind · 27.432B | Q8_0recommended | 33.4 GB | ~14.9–21.4 t/s | ~529–1100 t/s | 128K | Comfortable | Estimated |
| Qwen3.8 27B Alibaba Qwen · 27.781B | Q8_0recommended | 30.4 GB | ~14.7–21.1 t/s | ~522–1080 t/s | 256K | Comfortable | Estimated |
| Qwen3.6 27B Alibaba Qwen · 27.781B | Q8_0recommended | 30.4 GB | ~14.7–21.1 t/s | ~522–1080 t/s | 256K | Comfortable | Estimated |
| Granite 4.2 30B IBM · 29.277B | Q8_0recommended | 33.4 GB | ~13.9–20.1 t/s | ~496–1030 t/s | 128K | Comfortable | Estimated |
| Gemma 4 31B Google DeepMind · 31.273B | Q8_0recommended | 41.0 GB | ~13.1–18.8 t/s | ~464–964 t/s | 64K | Comfortable | Estimated |
| Qwen3 32B Alibaba Qwen · 32.762B | Q8_0recommended | 37.1 GB | ~12.5–18 t/s | ~443–920 t/s | 40K | Comfortable | Estimated |
| DeepSeek-R1-Distill 32B DeepSeek · 32.764B | Q8_0recommended | 37.1 GB | ~12.5–18 t/s | ~443–920 t/s | 128K | Comfortable | Estimated |
| Llama 3.3 70B Meta · 70.554B | Q8_0recommended | 76.8 GB | ~5.8–8.4 t/s | ~206–427 t/s | 96K | Comfortable | Estimated |
Rows in grey are estimates from our bandwidth model, not measurements — they are shown as a range and never as a precise figure. Use the “measured only” filter to see just the 0 pairings on this machine that a real benchmark backs.
Submit a benchmarkContributions are reviewed before publication.
Ownership economicsUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$45
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $55 less
Net cash at purchase
$4,323
Calculated VAT not reclaimable
Total over 5 years
$2,716
Calculated after tax, after resale
Cost per USD/1M tokens
$1.85
Calculated 24.5M 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.
Purchase-price input: $4,323 in United States (federal), tax/VAT excluded · estimated · Apple Store NL (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 3,026 over 5 years, straight-line to a 1,297 residual | $50.44 |
| Electricity 5.4 kWh/month at 0.140/kWh | $0.76 |
| Cost of capital 4.0%/yr on 2,810 average capital employed | $9.37 |
| Monthly cost before tax | $60.56 |
| Electricity tax shield Running costs are deductible business expenses | −$0.16 |
| First-year expensing §179 (100.0%) | −$15.13 |
| Monthly economic cost after tax | $45.27 |
Three different numbers, deliberately
Cash cost
$4,323
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$50.44/month
$3,026 written down over 5 years to a $1,297 residual.
After-tax economic cost
$45.27/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
$1,297 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.140/kWh Assumption
Average power draw
31 W Calculated
Load 122 W for 20% of powered hours, idle 8 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $908 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$9.37/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.