Editing a copy of Used RTX 3090 workhorse
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 490 W of 850 W · spikes to 700 W
Best fit:Qwen 3.8 27BQ5_K_Mat 32k, 25 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | 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 | $3,343 | 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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q5_K_M | fits | 22.5 GB | 44k78k with q8 cache | 25tok/sest. | 515 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 21.2 GB | 64k112k with q8 cache | 27tok/sest. | 515 tok/s | chat, coding |
| Gemma 4 31B | Q4_K_M | fits | 21.2 GB | 57k110k with q8 cache | 27tok/sest. | 459 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.3 GB | 74k116k with q8 cache | 134tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 21.3 GB | 62k110k with q8 cache | 27tok/sest. | 515 tok/s | chat, coding |
| Gemma 4 26B-A4B | UD-Q6_K | fits | 23.3 GB | 36k62k with q8 cache | 78tok/sest. | 3273 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.1 GB | 84k131k with q8 cache | 135tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 22.5 GB | 48k82k with q8 cache | 65tok/sest. | 1921 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q5_K_M | fits | 21.5 GB | 43k79k with q8 cache | 26tok/sest. | 544 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.9 GB | 128k | 108tok/sest. | 2747 tok/s | chat, coding, agents, long documents |
$3,343
No problems found