modelrigs

gpt-oss-20b on Framework Desktop (Ryzen AI Max+ 395, 64 GB)

20.915B (3.6B active) on 64 GB at 256 GB/s. Hardware details · Model details

Run locally →
Yes. gpt-oss-20b fits on Framework Desktop (Ryzen AI Max+ 395, 64 GB) at the recommended MXFP4 configuration, requiring approximately 13.0 GB at 8K context. Practical context capacity is 128K.
CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
MXFP4
Calculated gguf
Memory required
13.0 GB
Calculated of 52.5 GB usable — 25%
Max practical context
128K
Calculated model supports 128K

Memory budget at 8K context

Model weights ⓘ
11.3 GB Calculated
KV cache ⓘ
0.4 GB Calculated
Runtime overhead ⓘ
1.3 GB Estimated
Total required
13.0 GB Calculated
Headroom ⓘ
39.5 GB Calculated
Highest-precision quantization that leaves headroom: uses 25% of usable memory at 8K context.
Unified LPDDR: the accelerator allocates from the same 64 GB pool as the OS. We assume 82% is available to the inference engine.
Mixture of experts: all 20.915B parameters must be resident in memory even though only ~3.6B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended MXFP4

Decode, prefill and TTFT below are estimates for MXFP4. We do not have a comparable MXFP4 measurement on this machine.

Estimated decode
—
Estimated MXFP4; calculated range
Estimated prefill
—
Estimated MXFP4; calculated range
Estimated TTFT at 8K
—
Estimated MXFP4; calculated range
Hardware load reference
120 W
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 3.6B active parameters at 4.25 bits/weight takes 15.49 ms at 256 GB/s x 48% 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
MXFP4recommended11.3 GB11.3 GB13.0 GB25%Comfortable128K
BF1639.0 GB39.0 GB41.5 GB79%Comfortable128K
Cost of running gpt-oss-20b on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$1
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $99 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$41
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
6.3 kWh/month at 0.140/kWh
$0.88
Monthly cost before tax$0.88
Electricity tax shield
Running costs are deductible business expenses
−$0.18
Monthly economic cost after tax$0.69

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
$0.69/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 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
36 W Calculated
Load 120 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 $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.
gpt-oss-20b on other hardware
HardwareDecodePriceFit
NVIDIA DGX H200 (8x H200, 1,128 GB)~553–796 t/s$359,430 *Comfortable
Quad RTX 5090 workstation (4x 32 GB)~387–556 t/s$12,611 *Comfortable
Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)~366–527 t/s$58,553 *Comfortable
RTX 5090 workstation (1x 32 GB)419 t/s$3,332 *Comfortable
RTX PRO 6000 Blackwell workstation (96 GB)~329–474 t/s$10,359 *Comfortable
RTX PRO 6000 Max-Q workstation (96 GB, 300 W)~329–474 t/s$10,809 *Comfortable
Nearest alternatives to the Framework Desktop (Ryzen AI Max+ 395, 64 GB)
gpt-oss-20b on Framework Desktop (Ryzen AI Max+ 395, 128 GB)128 GBgpt-oss-20b on GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)128 GBgpt-oss-20b on NVIDIA DGX Spark 128 GB128 GBgpt-oss-20b on Dual RTX 5090 workstation (2x 32 GB)64 GBgpt-oss-20b on Mac Studio M1 Max 64 GB64 GB
Compare Framework Desktop (Ryzen AI Max+ 395, 64 GB) against Framework Desktop (Ryzen AI Max+ 395, 128 GB) →