Editing a copy of RTX 5070 Ti 16GB coding box
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 440 W of 850 W · spikes to 620 W
Best fit:gpt-oss 20BMXFP4at 32k, 103 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 5070 Ti 16 GB · 896 GB/s · 300 W | $995 | Buy | |
| GPU 2optional | ||||
| CPU | AMD Ryzen 7 7700 AM5 · 8 cores · 24 PCIe lanes | Not sold here | – | |
| Motherboard | MSI MAG B650 Tomahawk WiFi AM5 · DDR5 · ATX | $140 | Buy | |
| Memory | G.Skill Flare X5 64GB (2×32GB) DDR5-6000 64 GB · DDR5-6000 | $1,133 | Buy | |
| Storage | Samsung 990 Pro 2TB 2000 GB NVME | $300 | Buy | |
| Power supply | Corsair RM850x ATX 3.1 850W 850 W · ATX 3 | $90 | Buy | |
| Case | Fractal Design North GPUs up to 355 mm | $80 | Buy | |
| Total + 1 without a price | $2,738 | Prices checked 2 h ago | ||
Notes
- Note: Check the power connectors on the card you buy: this power supply has 1 12V-2x6 and 3 8-pin PCIe connectors.
- Note: Fractal Design North fits graphics cards up to 355 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 |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.9 GB | 116k128k with q8 cache | 103tok/sest. | 3404 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.5 GB | 120k193k with q8 cache | 41tok/sest. | 1481 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 155k256k with q8 cache | 52tok/sest. | 1846 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 14.3 GB | 38k40k with q8 cache | 39tok/sest. | 922 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 14.8 GB | 35k64k with q8 cache | 37tok/sest. | 1025 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.5 GB | 44k81k with q8 cache | 41tok/sest. | 1520 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.5 GB | 40k | 41tok/sest. | 1520 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 256k | 99tok/sest. | 3453 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.5 GB | 45k82k with q8 cache | 41tok/sest. | 1469 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.6 GB | 36k67k with q8 cache | 38tok/sest. | 1398 tok/s | chat, coding, agents |
$2,738
No problems found