Mac Studio M5 Max 36 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.
ApplesystemAvailable16 models fit0 measured
Memory
36 GB
Official spec LPDDR5X unified
Memory bandwidth
614 GB/s
Official spec ~88% achieved in practice
Specifications
CPU
Apple M5 Max, 18-core (6 super + 12 performance) Official spec
GPU
32-core GPU with Neural Accelerators Official spec
Memory
36 GB LPDDR5X unified Official spec
Memory bandwidth
614 GB/s Official spec source
Achieved bandwidth ⓘ
~88% (538 GB/s) Assumption
FP16 compute ⓘ
~96 TFLOPS Estimated
Architecture
Unified memory (CPU and GPU share one pool) Official spec
Nominal power
160 W Official spec
Measured load power
105 W Measured
Idle power
7 W Measured
Released
22 Sept 2026 Official spec
Base configuration, 512 GB SSD. 36 GB is enough for 27B-class dense models at 4-bit but not for the large MoEs that make a Mac Studio interesting. computeTflopsFp16 is an ESTIMATE derived from the measured 3.4x prefill improvement of M5 Max over M4 Max in llama.cpp; Apple does not publish FP16 matmul throughput. Achieved-bandwidth coefficient INHERITED from mac-studio-m5-max-128gb, which shares the same silicon and software stack.
Standout models on this machine
Fastest
gpt-oss-20b — ~158–228 t/s
MXFP4 · estimated confidence
Largest that fits
Related hardware
Model performance on Mac Studio M5 Max 36 GB0 measured, 16 estimated
16 of 16 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 | ~1340–2780 t/s | 128K | Comfortable | Estimated |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA · 31.578B (3B active) | Q5_K_Mrecommended | 23.3 GB | ~145–208 t/s | ~1190–2480 t/s | 1024K | Comfortable | Estimated |
| Qwen3-Coder 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q5_K_Mrecommended | 23.2 GB | ~134–192 t/s | ~1160–2400 t/s | 64K | Comfortable | Estimated |
| Qwen3 30B-A3B Alibaba Qwen · 30.532B (3.3B active) | Q5_K_Mrecommended | 23.2 GB | ~134–192 t/s | ~1160–2400 t/s | 40K | Comfortable | Estimated |
| Gemma 4 26B-A4B Google DeepMind · 25.806B (3.8B active) | Q5_K_Mrecommended | 21.0 GB | ~119–171 t/s | ~1170–2430 t/s | 32K | Comfortable | Estimated |
| Qwen3 8B Alibaba Qwen · 8.191B | Q8_0recommended | 10.6 GB | ~47.7–68.7 t/s | ~1420–2940 t/s | 40K | Comfortable | Estimated |
| Phi-4 14B Microsoft · 14.66B | Q8_0recommended | 17.8 GB | ~27.4–39.4 t/s | ~792–1640 t/s | 16K | Comfortable | Estimated |
| Devstral Small 24B Mistral AI · 23.572B | Q5_K_Mrecommended | 18.8 GB | ~25.5–36.7 t/s | ~492–1020 t/s | 64K | Comfortable | Estimated |
| Mistral Small 3.2 24B Mistral AI · 24.011B | Q5_K_Mrecommended | 19.1 GB | ~25–36 t/s | ~483–1000 t/s | 64K | Comfortable | Estimated |
| Gemma 4 31B Google DeepMind · 31.273B | Q4_K_Mrecommended | 27.2 GB | ~22.6–32.6 t/s | ~371–771 t/s | 8K | Fits | Estimated |
| Gemma 3 27B Google DeepMind · 27.432B | Q5_K_Mrecommended | 24.2 GB | ~22–31.7 t/s | ~423–879 t/s | 16K | Comfortable | Estimated |
| Qwen3.8 27B Alibaba Qwen · 27.781B | Q5_K_Mrecommended | 21.0 GB | ~21.7–31.3 t/s | ~418–868 t/s | 128K | Comfortable | Estimated |
| Qwen3.6 27B Alibaba Qwen · 27.781B | Q5_K_Mrecommended | 21.0 GB | ~21.7–31.3 t/s | ~418–868 t/s | 128K | Comfortable | Estimated |
| Qwen3 32B Alibaba Qwen · 32.762B | Q4_K_Mrecommended | 22.6 GB | ~21.6–31.1 t/s | ~354–736 t/s | 32K | Comfortable | Estimated |
| DeepSeek-R1-Distill 32B DeepSeek · 32.764B | Q4_K_Mrecommended | 22.6 GB | ~21.6–31.1 t/s | ~354–736 t/s | 32K | Comfortable | Estimated |
| Granite 4.2 30B IBM · 29.277B | Q5_K_Mrecommended | 23.6 GB | ~20.7–29.7 t/s | ~397–824 t/s | 32K | 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
$28
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $72 less
Net cash at purchase
$2,702
Calculated VAT not reclaimable
Total over 5 years
$1,706
Calculated after tax, after resale
Cost per USD/1M tokens
$1.16
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: $2,702 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 1,891 over 5 years, straight-line to a 810 residual | $31.52 |
| Electricity 4.7 kWh/month at 0.140/kWh | $0.66 |
| Cost of capital 4.0%/yr on 1,756 average capital employed | $5.85 |
| Monthly cost before tax | $38.03 |
| Electricity tax shield Running costs are deductible business expenses | −$0.14 |
| First-year expensing §179 (100.0%) | −$9.46 |
| Monthly economic cost after tax | $28.43 |
Three different numbers, deliberately
Cash cost
$2,702
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$31.52/month
$1,891 written down over 5 years to a $810 residual.
After-tax economic cost
$28.43/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
$810 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.140/kWh Assumption
Average power draw
27 W Calculated
Load 105 W for 20% of powered hours, idle 7 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $567 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$5.85/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.