modelrigs

DeepSeek Coder V2 236B-A21B on MacBook Pro M3 Max 128 GB

235.741B (21B active) on 128 GB at 400 GB/s. Hardware details · Model details

No calculated fit. DeepSeek Coder V2 236B-A21B does not fit under standard overhead assumptions at MLX 4-bit: the model calculates 133.8 GB required against 108.8 GB usable.
CompatibilityDoes not fit
Calculated fit
No
Calculated Requires more than 97% of usable memory. Needs a smaller quantization or more memory.
Smallest catalogued quantization
MLX 4-bit
Calculated mlx
Memory required
133.8 GB
Calculated of 108.8 GB usable — 123%
Max practical context
0
Calculated model supports 160K

Memory budget at 8K context

Model weights ⓘ
128.4 GB Calculated
KV cache ⓘ
0.5 GB Calculated
Runtime overhead ⓘ
4.9 GB Estimated
Total required
133.8 GB Calculated
Headroom ⓘ
-25.0 GB Calculated
No quantization in our catalogue fits this machine.
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 235.741B parameters must be resident in memory even though only ~21B are active per token. Memory follows total parameters; speed follows active parameters.
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
  1. Decode: reading 21.0B active parameters at 4.50 bits/weight takes 42.19 ms at 400 GB/s x 70% achieved efficiency.
  2. 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
QuantizationResidentDiskTotal neededUtilisationFitMax context
MLX 4-bitsmallest listed128.4 GB128.4 GB133.8 GB123%Does not fit0
Q4_K_M137.1 GB137.1 GB142.7 GB131%Does not fit0
Q5_K_M160.8 GB160.8 GB167.2 GB154%Does not fit0
Q8_0237.9 GB237.9 GB246.6 GB227%Does not fit0
BF16439.1 GB439.1 GB453.8 GB417%Does not fit0
Cost of running DeepSeek Coder V2 236B-A21B 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
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.
DeepSeek Coder V2 236B-A21B on other hardware
HardwareDecodePriceFit
Nearest alternatives to the MacBook Pro M3 Max 128 GB
DeepSeek Coder V2 236B-A21B on Mac Studio M1 Ultra 128 GB128 GBDeepSeek Coder V2 236B-A21B on Mac Studio M5 Max 128 GB128 GBDeepSeek Coder V2 236B-A21B on MacBook Pro M4 Max 128 GB128 GBDeepSeek Coder V2 236B-A21B on Mac Studio M2 Max 96 GB96 GBDeepSeek Coder V2 236B-A21B on Mac Studio M3 Ultra 96 GB96 GB
Compare MacBook Pro M3 Max 128 GB against Mac Studio M1 Ultra 128 GB →