gpt-oss-120b on Radeon RX 7900 XT 20 GB
116.829B (5.1B active) on 20 GB at 800 GB/s. Hardware details · Model details
No calculated fit. gpt-oss-120b does not fit under standard overhead assumptions at
MXFP4: the model calculates 66.5 GB required against 18.4 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
MXFP4
Calculated gguf
Memory required
66.5 GB
Calculated of 18.4 GB usable — 361%
Max practical context
0
Calculated model supports 128K
Memory budget at 8K context
Model weights ⓘ
63.0 GB Calculated
KV cache ⓘ
0.6 GB Calculated
Runtime overhead ⓘ
2.9 GB Estimated
Total required
66.5 GB Calculated
Headroom ⓘ
-48.1 GB Calculated
No quantization in our catalogue fits this machine.
Discrete GPU: 20 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 116.829B parameters must be resident in memory even though only ~5.1B 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
315 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
- Decode: reading 5.1B active parameters at 4.25 bits/weight takes 4.84 ms at 800 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 |
|---|---|---|---|---|---|---|
MXFP4smallest listed | 63.0 GB | 63.0 GB | 66.5 GB | 361% | Does not fit | 0 |
BF16 | 217.6 GB | 217.6 GB | 225.7 GB | 1227% | Does not fit | 0 |
Cost of running gpt-oss-120b on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$2
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $98 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$109
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 16.4 kWh/month at 0.140/kWh | $2.30 |
| Monthly cost before tax | $2.30 |
| Electricity tax shield Running costs are deductible business expenses | −$0.48 |
| Monthly economic cost after tax | $1.81 |
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
$1.81/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
93 W Calculated
Load 315 W for 20% of powered hours, idle 38 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.
gpt-oss-120b on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| NVIDIA DGX H200 (8x H200, 1,128 GB) | ~541–778 t/s | $359,430 * | Comfortable |
| Quad RTX 5090 workstation (4x 32 GB) | ~339–487 t/s | $12,611 * | Comfortable |
| Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) | ~317–456 t/s | $58,553 * | Comfortable |
| Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB) | ~259–373 t/s | $36,663 * | Comfortable |
| RTX PRO 6000 Blackwell workstation (96 GB) | ~257–369 t/s | $10,359 * | Comfortable |
| RTX PRO 6000 Max-Q workstation (96 GB, 300 W) | ~257–369 t/s | $10,809 * | Comfortable |
Nearest alternatives to the Radeon RX 7900 XT 20 GB