Editing a copy of Dual used RTX 3090 48GB
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 895 W of 1200 W · spikes to 1315 W
Best fit:Qwen 3.8 27BQ8_0at 32k, 19 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | Buy | |
| GPU 2optional | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | Buy | |
| CPU | AMD Ryzen 9 9900X AM5 · 12 cores · 24 PCIe lanes | $300 | Buy | |
| Motherboard | ASUS ProArt X870E-Creator WiFi AM5 · DDR5 · ATX | $539 | Buy | |
| Memory | Corsair Vengeance 128GB (4×32GB) DDR5-5200 128 GB · DDR5-5200 | Not sold here | – | |
| Storage | Samsung 990 Pro 2TB 2000 GB NVME | $300 | Buy | |
| Power supply | Seasonic Vertex GX-1200 1200W 1200 W · ATX 3 | $324 | Buy | |
| Case | Fractal Design Torrent GPUs up to 461 mm | $200 | Buy | |
| Total + 1 without a price | $4,863 | 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: The second x16 slot is 3 slots below the first: choose cards no thicker than 3 slots, or the top card covers it.
- Note: Fractal Design Torrent fits graphics cards up to 461 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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.5 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 41.1 GB | 224k256k with q8 cache | 81tok/sest. | 1208 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Gemma 4 31B | Q8_0 | fits | 35.0 GB | 172k256k with q8 cache | 16tok/sest. | 459 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 39.4 GB | 296k471k with q8 cache | 111tok/sest. | 1343 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 91tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.1 GB | 256k | 69tok/sest. | 3273 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 91tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.6 GB | 198k | 49tok/sest. | 1921 tok/s | chat, coding, agents, long documents |
$4,863
No problems found