Editing a copy of Used RTX 3060 12GB starter
Choose parts or a complete machine. Compatibility, the total and what it runs update as you go, and nothing is saved until you share it.
Compatibility: No problems found.Est. load 310 W of 650 W · spikes to 412 W
Best fit:Gemma 4 12BQ6_Kat 32k, 21 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 3060 12GB 12 GB · 360 GB/s · 170 W | $360 | Buy | |
| GPU 2optional | ||||
| CPU | Intel Core i5-12400F LGA1700 · 6 cores · 20 PCIe lanes | $150 | Buy | |
| Motherboard | MSI PRO B760-P WiFi DDR4 LGA1700 · DDR4 · ATX | $135 | Buy | |
| Memory | Corsair Vengeance LPX 32GB (2×16GB) DDR4-3600 32 GB · DDR4-3600 | Not sold here | – | |
| Storage | Crucial P3 Plus 1TB 1000 GB NVME | $179 | Buy | |
| Power supply | MSI MAG A650BN 650W 650 W | $45 | Buy | |
| Case | Corsair 4000D Airflow GPUs up to 360 mm | $40 | Buy | |
| Total + 1 without a price | $909 | Prices checked 2 h ago | ||
Notes
- Note: Check the power connectors on the card you buy: this power supply has 0 12V-2x6 and 2 8-pin PCIe connectors.
- Note: Corsair 4000D Airflow fits graphics cards up to 360 mm: check the length of the card you buy.
What this build runs
The most precise quant that fits, for every model in the catalogue. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q6_K | fits | 10.8 GB | 59k100k with q8 cache | 21tok/sest. | 431 tok/s | chat, coding |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 47k79k with q8 cache | 21tok/sest. | 537 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q5_K_M | fits | 10.8 GB | 35k65k with q8 cache | 21tok/sest. | 442 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q5_K_M | fits | 10.8 GB | 35k40k with q8 cache | 21tok/sest. | 442 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 174k256k with q8 cache | 40tok/sest. | 1005 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q5_K_M | fits | 10.8 GB | 36k66k with q8 cache | 21tok/sest. | 427 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | fits | 11.0 GB | 34k62k with q8 cache | 21tok/sest. | 407 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 91k128k with q8 cache | 24tok/sest. | 675 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 43k75k with q8 cache | 50tok/sest. | 2206 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 34k63k with q8 cache | 21tok/sest. | 467 tok/s | chat, coding |
$909
No problems found