Qwen2.5 14B on Radeon RX 6900 XT 16 GB
14.77B on 16 GB at 512 GB/s. Hardware details · Model details
Yes. Qwen2.5 14B fits on Radeon RX 6900 XT 16 GB at the recommended
Q4_K_M configuration, requiring approximately 11.3 GB at 8K context. Practical context capacity is 16K.CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
Q4_K_M
Calculated gguf
Memory required
11.3 GB
Calculated of 14.7 GB usable — 77%
Max practical context
16K
Calculated model supports 32K
Memory budget at 8K context
Model weights ⓘ
8.6 GB Calculated
KV cache ⓘ
1.5 GB Calculated
Runtime overhead ⓘ
1.3 GB Estimated
Total required
11.3 GB Calculated
Headroom ⓘ
3.4 GB Calculated
Highest-precision quantization that leaves headroom: uses 77% of usable memory at 8K context.
Discrete GPU: 16 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
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
—
Estimated Q4_K_M; calculated range
Hardware load reference
300 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 14.8B active parameters at 4.85 bits/weight takes 24.98 ms at 512 GB/s x 70% achieved efficiency.
- 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 |
|---|---|---|---|---|---|---|
Q4_K_Mrecommended | 8.6 GB | 8.6 GB | 11.3 GB | 77% | Comfortable | 16K |
Q5_K_M | 10.1 GB | 10.1 GB | 12.9 GB | 87% | Fits | 8K |
Q8_0 | 14.9 GB | 14.9 GB | 17.9 GB | 121% | Does not fit | 0 |
BF16 | 27.5 GB | 27.5 GB | 30.8 GB | 209% | Does not fit | 0 |
Cost of running Qwen2.5 14B 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
$104
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 15.6 kWh/month at 0.140/kWh | $2.19 |
| Monthly cost before tax | $2.19 |
| Electricity tax shield Running costs are deductible business expenses | −$0.46 |
| Monthly economic cost after tax | $1.73 |
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
$1.73/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
89 W Calculated
Load 300 W for 20% of powered hours, idle 36 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.
Qwen2.5 14B on other hardware
| Hardware | Decode | Price | Fit |
|---|
Nearest alternatives to the Radeon RX 6900 XT 16 GB