DeepSeek-V4 Flash on GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)
304.18B (13B active) on 128 GB at 256 GB/s. Hardware details · Model details
Yes. DeepSeek-V4 Flash fits on GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB) at the recommended
DS4 Q2 (mixed) configuration, requiring approximately 85.1 GB at 8K context. Practical context capacity is 192K.CompatibilityFits
Calculated fit
Yes
Calculated Uses 80-90% of usable memory. Works, with limited headroom.
Recommended quantization
DS4 Q2 (mixed)
Calculated gguf
Memory required
85.1 GB
Calculated of 105.0 GB usable — 81%
Max practical context
192K
Calculated model supports 1M
Memory budget at 8K context
Model weights ⓘ
81.0 GB Measured
KV cache ⓘ
0.7 GB Calculated
Runtime overhead ⓘ
3.4 GB Estimated
Total required
85.1 GB Calculated
Headroom ⓘ
19.9 GB Calculated
Fits with limited headroom (81% of usable memory). A longer context will not leave room for much else.
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 304.18B parameters must be resident in memory even though only ~13B are active per token. Memory follows total parameters; speed follows active parameters.
Performance
Estimated performance · recommended DS4 Q2 (mixed)
Decode, prefill and TTFT below are estimates for DS4 Q2 (mixed). We do not have a comparable DS4 Q2 (mixed) measurement on this machine.
Estimated decode
—
Estimated DS4 Q2 (mixed); calculated range
Estimated prefill
—
Estimated DS4 Q2 (mixed); calculated range
Estimated TTFT at 8K
~71.9–149.3 s
Estimated DS4 Q2 (mixed); 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
- Decode: reading 13.0B active parameters at 2.29 bits/weight takes 34.73 ms at 256 GB/s x 42% achieved efficiency.
- MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
- Prefill: 59 TFLOPS (FP16) x 18% assumed model-FLOPs utilisation, divided by 2 x 62.9B parameters per token.
- Prefill uses 62.9B effective parameters, not the 13B 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
| Quantization | Resident | Disk | Total needed | Utilisation | Fit | Max context |
|---|---|---|---|---|---|---|
DS4 Q2 (mixed)recommended | 81.0 GB | 81.0 GB | 85.1 GB | 81% | Fits | 192K |
Q4_K_M | 176.9 GB | 176.9 GB | 183.9 GB | 175% | Does not fit | 0 |
Q5_K_M | 207.5 GB | 207.5 GB | 215.4 GB | 205% | Does not fit | 0 |
Q8_0 | 307.0 GB | 307.0 GB | 317.9 GB | 303% | Does not fit | 0 |
Cost of running DeepSeek-V4 Flash 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
- 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.
DeepSeek-V4 Flash on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| NVIDIA DGX H200 (8x H200, 1,128 GB) | ~411–592 t/s | $359,430 * | Comfortable |
| Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) | ~150–216 t/s | $58,553 * | Comfortable |
| Mac Studio M5 Ultra 256 GB | ~89.3–129 t/s | $8,647 * | Comfortable |
| Mac Studio M3 Ultra 256 GB | ~51.8–74.5 t/s | $5,674 * | Comfortable |
| NVIDIA DGX Station GB300 (748 GB) | ~50.4–72.6 t/s | $90,082 * | Comfortable |
| Mac Studio M5 Ultra 512 GB | ~49.8–71.7 t/s | $11,350 * | Comfortable |
Nearest alternatives to the GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)
DeepSeek-V4 Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB)128 GBDeepSeek-V4 Flash on Framework Desktop (Ryzen AI Max+ 395, 64 GB)64 GBDeepSeek-V4 Flash on NVIDIA DGX Spark 128 GB128 GBDeepSeek-V4 Flash on CPU-only workstation (Ryzen 9950X, 192 GB DDR5)192 GBDeepSeek-V4 Flash on Mac Studio M5 Max 128 GB128 GB
Compare GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB) against Framework Desktop (Ryzen AI Max+ 395, 128 GB) →
Compare GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB) against Framework Desktop (Ryzen AI Max+ 395, 128 GB) →