Qwen3.5 122B-A10B on Mac Studio M2 Max 96 GB
125.086B (10B active) on 96 GB at 400 GB/s. Hardware details · Model details
Yes. Qwen3.5 122B-A10B fits on Mac Studio M2 Max 96 GB at the recommended
MLX 4-bit configuration, requiring approximately 71.4 GB at 8K context. Practical context capacity is 256K.CompatibilityFits
Calculated fit
Yes
Calculated Uses 80-90% of usable memory. Works, with limited headroom.
Recommended quantization
MLX 4-bit
Calculated mlx
Memory required
71.4 GB
Calculated of 81.6 GB usable — 87%
Max practical context
256K
Calculated model supports 256K
Memory budget at 8K context
Model weights ⓘ
68.1 GB Calculated
KV cache ⓘ
0.2 GB Calculated
Runtime overhead ⓘ
3.0 GB Estimated
Total required
71.4 GB Calculated
Headroom ⓘ
10.2 GB Calculated
Fits with limited headroom (87% of usable memory). A longer context will not leave room for much else.
Unified memory: weights, KV cache and the OS share the same 96 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 125.086B parameters must be resident in memory even though only ~10B are active per token. Memory follows total parameters; speed follows active parameters.
Hybrid attention: token-growing KV memory is charged to 12 full-attention blocks. The linear-attention blocks also hold fixed-size state, so the memory estimate is approximate.
Performance
Estimated performance · recommended MLX 4-bit
Decode, prefill and TTFT below are estimates for MLX 4-bit. We do not have a comparable MLX 4-bit measurement on this machine.
Estimated decode
—
Estimated MLX 4-bit; calculated range
Estimated prefill
—
Estimated MLX 4-bit; calculated range
Estimated TTFT at 8K
—
Estimated MLX 4-bit; calculated range
Hardware load reference
—
Official spec hardware TDP; not this model run
No throughput figures for this configuration. We do not estimate performance for a model that cannot load.
How the estimate is calculated
- Decode: reading 10.0B active parameters at 4.50 bits/weight takes 20.09 ms at 400 GB/s x 70% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
- No FP16 compute figure for this hardware, so prefill cannot be estimated.
- 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.
Submit a benchmarkSubmissions stay pending until reviewed.
This model at other quantizations on this machine
| Quantization | Resident | Disk | Total needed | Utilisation | Fit | Max context |
|---|---|---|---|---|---|---|
MLX 4-bitrecommended | 68.1 GB | 68.1 GB | 71.4 GB | 87% | Fits | 256K |
Q4_K_M | 72.7 GB | 72.7 GB | 76.1 GB | 93% | Borderline | 128K |
Q5_K_M | 85.3 GB | 85.3 GB | 89.1 GB | 109% | Does not fit | 0 |
Q8_0 | 126.3 GB | 126.3 GB | 131.2 GB | 161% | Does not fit | 0 |
BF16 | 233.0 GB | 233.0 GB | 241.2 GB | 296% | Does not fit | 0 |
Cost of running Qwen3.5 122B-A10B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$0
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $100 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$0
Calculated after tax, after resale
Cost per USD/1M tokens
—
Calculated
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 0 over 5 years, straight-line to a 0 residual | $0.00 |
| Electricity 0.0 kWh/month at 0.140/kWh | $0.00 |
| Monthly cost before tax | $0.00 |
| Electricity tax shield Running costs are deductible business expenses | -$0.00 |
| Monthly economic cost after tax | $0.00 |
Three different numbers, deliberately
Cash cost
$0
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$0.00/month
$0 written down over 5 years to a $0 residual.
After-tax economic cost
$0.00/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
$0 (30%) Assumption
Extrapolated from the three-year curve.
Electricity
$0.000/kWh Assumption
Average power draw
0 W Calculated
Load — for 20% of powered hours, idle 0 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $0 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
not applied 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
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.
Qwen3.5 122B-A10B on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| NVIDIA DGX H200 (8x H200, 1,128 GB) | ~441–635 t/s | $359,430 * | Comfortable |
| Quad RTX 5090 workstation (4x 32 GB) | ~223–320 t/s | $12,611 * | Comfortable |
| Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) | ~135–195 t/s | $58,553 * | Comfortable |
| RTX PRO 6000 Blackwell workstation (96 GB) | ~133–192 t/s | $10,359 * | Fits |
| RTX PRO 6000 Max-Q workstation (96 GB, 300 W) | ~133–192 t/s | $10,809 * | Fits |
| Mac Studio M5 Ultra 96 GB | ~112–162 t/s | $5,945 * | Fits |
Nearest alternatives to the Mac Studio M2 Max 96 GB
Qwen3.5 122B-A10B on Mac Studio M3 Ultra 96 GB96 GBQwen3.5 122B-A10B on Mac Studio M5 Ultra 96 GB96 GBQwen3.5 122B-A10B on Mac Studio M1 Ultra 128 GB128 GBQwen3.5 122B-A10B on Mac Studio M5 Max 128 GB128 GBQwen3.5 122B-A10B on MacBook Pro M3 Max 128 GB128 GB
Compare Mac Studio M2 Max 96 GB against Mac Studio M3 Ultra 96 GB →
Compare Mac Studio M2 Max 96 GB against Mac Studio M3 Ultra 96 GB →