modelrigs

MiMo-V2.6 Pro 1.02T-A42B on GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)

1.0T (42B active) on 128 GB at 256 GB/s. Hardware details · Model details

No calculated fit. MiMo-V2.6 Pro 1.02T-A42B does not fit under standard overhead assumptions at Q4_K_M: the model calculates 615.3 GB required against 105.0 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
Q4_K_M
Calculated gguf
Memory required
615.3 GB
Calculated of 105.0 GB usable — 586%
Max practical context
0
Calculated model supports 1M

Memory budget at 8K context

Model weights ⓘ
593.2 GB Calculated
KV cache ⓘ
3.3 GB Calculated
Runtime overhead ⓘ
18.8 GB Estimated
Total required
615.3 GB Calculated
Headroom ⓘ
-510.3 GB Calculated
No quantization in our catalogue fits this machine.
Unified LPDDR: the accelerator allocates from the same 128 GB pool as the OS. We assume 82% is available to the inference engine.
Mixture of experts: all 1020B parameters must be resident in memory even though only ~42B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended Q4_K_M

Decode, prefill and TTFT below are estimates for Q4_K_M. We do not have a comparable Q4_K_M measurement on this machine.

Estimated decode
—
Estimated Q4_K_M; calculated range
Estimated prefill
—
Estimated Q4_K_M; calculated range
Estimated TTFT at 8K
~236.8–490.7 s
Estimated Q4_K_M; calculated range
Hardware load reference
135 W
Measured machine-level load; 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 42.0B active parameters at 4.85 bits/weight takes 237.65 ms at 256 GB/s x 42% achieved efficiency.
  2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
  3. Prefill: 59 TFLOPS (FP16) x 18% assumed model-FLOPs utilisation, divided by 2 x 207.0B parameters per token.
  4. Prefill uses 207.0B effective parameters, not the 42B 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.

Submit a benchmarkSubmissions stay pending until reviewed.
This model at other quantizations on this machine
QuantizationResidentDiskTotal neededUtilisationFitMax context
Q4_K_Msmallest listed593.2 GB593.2 GB615.3 GB586%Does not fit0
Q5_K_M695.9 GB695.9 GB721.1 GB687%Does not fit0
Q8_01029.5 GB1029.5 GB1064.7 GB1014%Does not fit0
Cost of running MiMo-V2.6 Pro 1.02T-A42B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$22
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $78 less
Net cash at purchase
$1,711
Calculated VAT not reclaimable
Total over 5 years
$1,336
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.

Purchase-price input: $1,711 in United States (federal), tax/VAT excluded · estimated · GMKtec (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.

Monthly breakdown

Depreciation
1,454 over 5 years, straight-line to a 257 residual
$24.23
Electricity
6.7 kWh/month at 0.140/kWh
$0.94
Cost of capital
4.0%/yr on 984 average capital employed
$3.28
Monthly cost before tax$28.45
Electricity tax shield
Running costs are deductible business expenses
−$0.20
First-year expensing
§179 (100.0%)
−$5.99
Monthly economic cost after tax$22.27

Three different numbers, deliberately

Cash cost
$1,711
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$24.23/month
$1,454 written down over 5 years to a $257 residual.
After-tax economic cost
$22.27/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
$257 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
38 W Calculated
Load 135 W for 20% of powered hours, idle 14 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $359 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$3.28/month 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.
MiMo-V2.6 Pro 1.02T-A42B on other hardware
HardwareDecodePriceFit
NVIDIA DGX H200 (8x H200, 1,128 GB)~305–439 t/s$359,430 *Comfortable
NVIDIA DGX Station GB300 (748 GB)~28.2–40.5 t/s$90,082 *Borderline
Nearest alternatives to the GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)
MiMo-V2.6 Pro 1.02T-A42B on Framework Desktop (Ryzen AI Max+ 395, 128 GB)128 GBMiMo-V2.6 Pro 1.02T-A42B on NVIDIA DGX Spark 128 GB128 GBMiMo-V2.6 Pro 1.02T-A42B on CPU-only workstation (Ryzen 9950X, 192 GB DDR5)192 GBMiMo-V2.6 Pro 1.02T-A42B on Mac Studio M5 Max 128 GB128 GBMiMo-V2.6 Pro 1.02T-A42B on Radeon AI PRO R9700 workstation (32 GB)32 GB
Compare GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB) against Framework Desktop (Ryzen AI Max+ 395, 128 GB) →