Dual used RTX 3090 48GB
$4,863
Parts
Compatibility: No problems found.Est. load 895 W of 1200 W · spikes to 1315 W
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | eBay | Buy |
| GPU 2 | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | eBay | Buy |
| CPU | AMD Ryzen 9 9900X AM5 · 12 cores · 24 PCIe lanes | $300 | eBay | Buy |
| Motherboard | ASUS ProArt X870E-Creator WiFi AM5 · DDR5 · ATX | $539 | eBay | Buy |
| Memory | Corsair Vengeance 128GB (4×32GB) DDR5-5200 128 GB · DDR5-5200 | Not sold now | – | |
| Power supply | Seasonic Vertex GX-1200 1200W 1200 W · ATX 3 | $324 | eBay | Buy |
| Case | Fractal Design Torrent GPUs up to 461 mm | $200 | eBay | Buy |
| Storage | Samsung 990 Pro 2TB 2000 GB NVME | $300 | eBay | Buy |
| Total + 1 without a price | $4,863 | |||
- 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, at 8k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 256k | 20tok/sest. | 559 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.4 GB | 224k256k with q8 cache | 94tok/sest. | 1478 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 20tok/sest. | 559 tok/s | chat, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 14k23k with q8 cache | 132tok/sest. | 3735 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.9 GB | 172k256k with q8 cache | 17tok/sest. | 487 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.8 GB | 296k471k with q8 cache | 136tok/sest. | 1932 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 105tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 20tok/sest. | 559 tok/s | chat, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 256k | 77tok/sest. | 3649 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.8 GB | 18k34k with q8 cache | 41tok/sest. | 737 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 15k24k with q8 cache | 169tok/sest. | 4695 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 105tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 31.2 GB | 198k | 61tok/sest. | 2680 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 137k251k with q8 cache | 22tok/sest. | 630 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.8 GB | 256k | 102tok/sest. | 4990 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.9 GB | 588k802k with q8 cache | 135tok/sest. | 4552 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 132tok/sest. | 3466 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 32.1 GB | 155k256k with q8 cache | 87tok/sest. | 3465 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.6 GB | 40k | 16tok/sest. | 431 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 44tok/sest. | 1272 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 59tok/sest. | 1610 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 22tok/sest. | 630 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 128k | 20tok/sest. | 566 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.6 GB | 51k95k with q8 cache | 16tok/sest. | 451 tok/s | chat |
| Llama 3.3 70B Meta | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 13tok/sest. | 210 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 199k256k with q8 cache | 37tok/sest. | 1045 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 34tok/sest. | 971 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 59tok/sest. | 1700 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 59tok/sest. | 1700 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 34tok/sest. | 978 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 121tok/sest. | 3242 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 57tok/sest. | 1588 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 54tok/sest. | 1576 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 69tok/sest. | 1951 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 237tok/sest. | 11389 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 76tok/sest. | 1755 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 919tok/sest. | 23836 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 623tok/sest. | 16400 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 373tok/sest. | 6727 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.1 GB | 128k | 273tok/sest. | 7502 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.0 GB | 128k | 191tok/sest. | 4959 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.3 GB | 128k | 172tok/sest. | 4991 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.3 GB | 32k | 172tok/sest. | 4405 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 5.1 GB | 128k | 135tok/sest. | 3303 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.4 GB | 128k | 127tok/sest. | 3551 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.5 GB | 128k | 124tok/sest. | 5981 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 128k | 123tok/sest. | 5488 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.0 GB | 128k | 99tok/sest. | 4626 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 9.1 GB | 128k | 68tok/sest. | 1893 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 60tok/sest. | 1755 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 57tok/sest. | 1588 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.8 GB | 128k | 56tok/sest. | 1373 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.4 GB | 64k | 48tok/sest. | 1373 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 17.3 GB | 128k | 34tok/sest. | 952 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 22tok/sest. | 641 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 22tok/sest. | 641 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 22tok/sest. | 641 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 22tok/sest. | 630 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 32.1 GB | 65k120k with q8 cache | 17tok/sest. | 508 tok/s | chat |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 13tok/sest. | 210 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 92.0 GB | – | 7tok/sest. | 351 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 102.6 GB | – | 6tok/sest. | 341 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 74.9 GB | – | 3tok/sest. | 198 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 73.2 GB | – | 13tok/sest. | 881 tok/s | – |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 59.9 GB | – | 30tok/sest. | 2171 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 29tok/sest. | 1219 tok/s | chat, coding, long documents |
| GLM 4.5V Z.ai | Q4_K_M | offload | 61.8 GB | – | 10tok/sest. | 719 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 68.2 GB | – | 7tok/sest. | 683 tok/s | – |
| MiniMax M2.5 MiniMax | MXFP4 | offload | 118.4 GB | – | 6tok/sest. | 715 tok/s | – |
| MiniMax M2 MiniMax | Q4_K_M | offload | 131.9 GB | – | 5tok/sest. | 688 tok/s | – |
| MiniMax M2.1 MiniMax | Q4_K_M | offload | 131.9 GB | – | 5tok/sest. | 688 tok/s | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | offload | 147.5 GB | – | 2tok/sest. | 208 tok/s | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | offload | 156.2 GB | – | 2tok/sest. | 202 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 73.7 GB | – | 2tok/sest. | 91 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | offload | 127.6 GB | – | 1tok/sest. | 74 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.8 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.7 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 748.2 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 248.8 GB | – | – | – | – |