Gemma 3 27B on Mac Studio M5 Max 64 GB

27.432B on 64 GB at 614 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
Q8_0
Calculated gguf
Memory required
33.4 GB
Calculated of 54.4 GB usable — 61%
Max practical context
32K
Calculated model supports 128K

Memory budget at 8K context

Model weights
27.7 GB Calculated
KV cache
3.9 GB Calculated
Runtime overhead
1.8 GB Estimated
Total required
33.4 GB Calculated
Usable memory
54.4 GB Assumption
Headroom
21.0 GB Calculated
Highest-precision quantization that leaves headroom: uses 61% of usable memory at 8K context.
Unified memory: weights, KV cache and the OS share the same 64 GB pool. We assume 85% is addressable by the GPU, which matches a headless machine with the wired-memory limit raised.
PerformanceEstimated0/10
Decode (generation)
~14.9–21.4 t/s
Estimated calculated, not measured
Prefill (prompt)
~529–1100 t/s
Estimated
TTFT at 8K
~7.5–15.6 s
Estimated time to first token
Power while generating
118 W
Measured 0.60 tokens/s per watt
These figures are estimated, not measured. Nobody has published a benchmark of Gemma 3 27B 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
  1. Decode: reading 27.4B active parameters at 8.50 bits/weight takes 54.17 ms at 614 GB/s x 88% achieved efficiency.
  2. Prefill: 120 TFLOPS (FP16) x 1.69 calibrated against measured prefill on this platform x 22% assumed model-FLOPs utilisation, divided by 2 x 27.4B parameters per token.

  • 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
QuantizationWeightsTotal neededUtilisationFitMax context
MLX 4-bit14.9 GB20.3 GB37%Comfortable64K
Q4_K_M16.0 GB21.3 GB39%Comfortable64K
Q8_0recommended27.7 GB33.4 GB61%Comfortable32K
BF1651.1 GB57.5 GB106%Does not fit0
Cost of running Gemma 3 27B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$37
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $63 less
Net cash at purchase
$3,512
Calculated VAT not reclaimable
Total over 5 years
$2,213
Calculated after tax, after resale
Cost per USD/1M tokens
$16.06
Calculated 2.3M 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
2,459 over 5 years, straight-line to a 1,054 residual
$40.98
Electricity
5.3 kWh/month at 0.140/kWh
$0.74
Cost of capital
4.0%/yr on 2,283 average capital employed
$7.61
Monthly cost before tax$49.33
Electricity tax shield
Running costs are deductible business expenses
−$0.16
First-year expensing
§179 (100.0%)
−$12.29
Monthly economic cost after tax$36.88

Three different numbers, deliberately

Cash cost
$3,512
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$40.98/month
$2,459 written down over 5 years to a $1,054 residual.
After-tax economic cost
$36.88/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
$1,054 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.140/kWh Assumption
Average power draw
30 W Calculated
Load 118 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 $738 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$7.61/month Assumption
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
5.2 t/s
Calculated purchase price only
Decode per $100/month
49.1 t/s
Calculated after-tax ownership cost
Tokens per joule
0.60
Calculated same as tokens/s per watt
USD per 1M output tokens
$16.06
Calculated at 20% utilisation
Local versus hosted APIs
Hosted modelUSD/1M outputBreak-evenAPI at your volumeVerdictComparison type
Qwen3.8 Flash
Alibaba Cloud
$0.4223.9M/mo$4API cheaperDifferent model
DeepSeek-V4 Flash
DeepSeek
$0.6615.2M/mo$6API cheaperDifferent model
DeepSeek-V4 Pro
DeepSeek
$1.985.1M/mo$17API cheaperDifferent model
DeepSeek V4 Pro (Together)
Together AI
$4.401.7M/mo$49Local cheaperDifferent model
GLM-5.3
Z.ai
$4.402.4M/mo$36About equalDifferent model
Claude Haiku 4.5
Anthropic
$5.002.8M/mo$30API cheaperDifferent 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 $37/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.
Page quality score (why this page is or is not indexed)

10/13 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)
  • Well connected (18 internal links) (+1)