gpt-oss-120b on Mac Studio M5 Max 128 GB
116.829B (5.1B active) on 128 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
MXFP4
Calculated gguf
Memory required
66.5 GB
Calculated of 108.8 GB usable — 61%
Max practical context
128K
Calculated model supports 128K
Memory budget at 8K context
Model weights ⓘ
63.0 GB Calculated
KV cache ⓘ
0.6 GB Calculated
Runtime overhead ⓘ
2.9 GB Estimated
Total required
66.5 GB Calculated
Usable memory ⓘ
108.8 GB Assumption
Headroom
42.3 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 128 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 116.829B parameters must be resident in memory even though only ~5.1B are active per token. Memory follows total parameters; speed follows active parameters.
PerformanceEstimated0/10
Decode (generation)
~118–170 t/s
Estimated calculated, not measured
Prefill (prompt)
~594–1230 t/s
Estimated
TTFT at 8K
~6.7–13.9 s
Estimated time to first token
Power while generating
122 W
Measured 4.69 tokens/s per watt
These figures are estimated, not measured. Nobody has published a benchmark of gpt-oss-120b 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 5.1B active parameters at 4.25 bits/weight takes 5.04 ms at 614 GB/s x 88% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- Prefill: 120 TFLOPS (FP16) x 1.69 calibrated against measured prefill on this platform x 22% assumed model-FLOPs utilisation, divided by 2 x 24.4B parameters per token.
- Prefill uses 24.4B effective parameters, not the 5.1B 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 |
|---|---|---|---|---|---|
MXFP4recommended | 63.0 GB | 66.5 GB | 61% | Comfortable | 128K |
BF16 | 217.6 GB | 225.7 GB | 207% | Does not fit | 0 |
Cost of running gpt-oss-120b on this machineUnited 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
$2.47
Calculated 18.3M 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 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.
Efficiency metrics
Decode per $1,000 spent
33.4 t/s
Calculated purchase price only
Decode per $100/month
319.0 t/s
Calculated after-tax ownership cost
Tokens per joule
4.69
Calculated same as tokens/s per watt
USD per 1M output tokens
$2.47
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 | 29.4M/mo | $28 | API cheaper | Different model |
| DeepSeek-V4 Flash DeepSeek | $0.66 | 18.7M/mo | $44 | About equal | Different model |
| DeepSeek-V4 Pro DeepSeek | $1.98 | 6.2M/mo | $133 | Local cheaper | Different model |
| DeepSeek V4 Pro (Together) Together AI | $4.40 | 2.1M/mo | $388 | Local cheaper | Different model |
| GLM-5.3 Z.ai | $4.40 | 2.9M/mo | $285 | Local cheaper | Different model |
| Claude Haiku 4.5 Anthropic | $5.00 | 3.5M/mo | $238 | Local 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 $45/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.
gpt-oss-120b on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| Quad RTX 5090 workstation (4x 32 GB) | ~339–487 t/s | €13.999 | Comfortable |
| RTX PRO 6000 Blackwell workstation (96 GB) | ~257–369 t/s | €11.499 | Comfortable |
| RTX PRO 6000 Max-Q workstation (96 GB, 300 W) | ~257–369 t/s | €11.999 | Comfortable |
| Mac Studio M5 Ultra 512 GB | ~203–293 t/s | €12.599 | Comfortable |
| Mac Studio M5 Ultra 256 GB | ~203–293 t/s | €9.599 | Comfortable |
| Mac Studio M5 Ultra 96 GB | ~203–293 t/s | €6.599 | Fits |
Nearest alternatives to the Mac Studio M5 Max 128 GB
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 (16 internal links) (+1)