Illustrative build · sample prices
Used-3090 24 GB
The reference rig. A used RTX 3090 gives 24 GB at 936 GB/s, enough for every 24–32B model at Q4.
Data checked: 2026-10-12. Review interval shown below. Prices need review after 30 days; specifications and benchmark collections after 90 days. Dates describe the recorded check, not a live retailer quote.
- Verified Checked against the primary source (for example the model’s config.json on Hugging Face).
- Sourced Taken from a cited source; not yet independently checked.
- Estimate Calculated with the published formulas; not a measurement.
- Sample Placeholder data for layout; not a real figure.
- Not yet measured No public, citable score found for this benchmark yet. We never fill the gap with a guess.
Verified metadata is not a measured performance result. Only cited runs matching model, device, quant and recorded context can replace speed estimates. Estimates assume one stream and F16 KV cache, with a ±25% uncertainty band. A published run applies only to its recorded runtime and conditions; missing settings are unknown.
Evidence labels · Freshness policy · Calculation methodology
Includes the listed system parts. Excludes tax, shipping, peripherals, maintenance, financing and resale. Sample parts prices may differ from current hardware catalogue prices. Electricity assumes 420 W whole-system load for 4 h and 70 W idle for 20 h daily, 30 days at $0.15/kWh. Power is unmeasured.
Parts list
GPU price is sourced (eBay sold, Oct 2026); other parts are sample.
Part | Item | Price, USD |
|---|---|---|
| GPU | GeForce RTX 3090 24 GB (used | $1,200Sourced |
| CPU | Ryzen 5 7600 | $189Sample |
| Motherboard | B650 ATX | $149Sample |
| Memory | 64 GB DDR5-6000 (2×32) | $189Sample |
| Storage | 2 TB NVMe Gen4 | $119Sample |
| PSU | 850 W 80+ Gold | $109Sample |
| Case | Mesh mid-tower | $25Sample |
No affiliate links yet. Prices will be timestamped per retailer once tracking starts.
Expected speed
Reference models, default quant, 8k context.
Model | Verdict | tok/s |
|---|---|---|
| Gemma 3 27B IT | Fits | 31.8Estimate |
| Qwen3 30B-A3B | Fits | 199.8Estimate |
| Mistral Small 3.2 24B | Fits | 35.8Estimate |
Break-even card
Electricity $13.86/month (420 W × 4 h + 70 W idle × 20 h, $0.15/kWh).
Plan | Price / month | Months to break even |
|---|---|---|
| ChatGPT Plus | $20 | 322.5 |
| Claude Pro | $20 | 322.5 |
| Google AI Pro | $19.99 | 323.0 |
| Claude Max (5×) | $100 | 23.0 |
| ChatGPT Pro 100 | $100 | 23.0 |
| Google AI Ultra (5×) | $99.99 | 23.0 |
| Claude Max (20×) | $200 | 10.6 |
| ChatGPT Pro 200 | $200 | 10.6 |
| Google AI Ultra (20×) | $199.99 | 10.6 |
| ChatGPT Pro 500 (top tier) | $500 | 4.1 |
Break-even = hardware ÷ (plan − electricity). It ignores capability: a local model is not a frontier model. Adjust the numbers.