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 64k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.7 GB | 256k | 17tok/sest. | 467 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 42.1 GB | 224k256k with q8 cache | 68tok/sest. | 972 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 18tok/sest. | 467 tok/s | chat, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.7 GB | 172k256k with q8 cache | 15tok/sest. | 426 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 40.3 GB | 296k471k with q8 cache | 90tok/sest. | 955 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 78tok/sest. | 2810 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 18tok/sest. | 467 tok/s | chat, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.9 GB | 256k | 61tok/sest. | 2877 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 78tok/sest. | 2810 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.4 GB | 198k | 39tok/sest. | 1394 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 137k251k with q8 cache | 16tok/sest. | 460 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.5 GB | 256k | 92tok/sest. | 3465 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.7 GB | 588k802k with q8 cache | 115tok/sest. | 2257 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 86tok/sest. | 2151 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.7 GB | 155k256k with q8 cache | 36tok/sest. | 1006 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 42.5 GB | 40k | 13tok/sest. | 238 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 41tok/sest. | 1106 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 50tok/sest. | 1354 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.6 GB | 128k | 17tok/sest. | 523 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 16tok/sest. | 460 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 42.5 GB | 80k128k with q8 cache | 13tok/sest. | 295 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.8 GB | 199k256k with q8 cache | 23tok/sest. | 647 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.1 GB | 40k | 22tok/sest. | 567 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 128k | 32tok/sest. | 895 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 32tok/sest. | 895 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.5 GB | 16k | 20tok/sest. | 569 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 87tok/sest. | 2347 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 256k | 32tok/sest. | 885 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 128k | 29tok/sest. | 818 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 57tok/sest. | 1773 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 81tok/sest. | 3784 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 128k | 38tok/sest. | 961 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 32k | 434tok/sest. | 8393 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.0 GB | 256k | 355tok/sest. | 9516 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.6 GB | 256k | 257tok/sest. | 5188 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.0 GB | 128k | 154tok/sest. | 3476 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.6 GB | 128k | 106tok/sest. | 1959 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.4 GB | 128k | 96tok/sest. | 3507 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.9 GB | 128k | 84tok/sest. | 2376 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.9 GB | 32k | 84tok/sest. | 2234 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.0 GB | 128k | 66tok/sest. | 2412 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.8 GB | 128k | 65tok/sest. | 1492 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.1 GB | 128k | 63tok/sest. | 1540 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.5 GB | 128k | 49tok/sest. | 1126 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 30.2 GB | 128k | 47tok/sest. | 2168 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.3 GB | 128k | 46tok/sest. | 760 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.9 GB | 64k | 40tok/sest. | 760 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.4 GB | 128k | 34tok/sest. | 961 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.4 GB | 256k | 32tok/sest. | 885 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 28.1 GB | 128k | 20tok/sest. | 517 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 16tok/sest. | 466 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 34.8 GB | 40k | 16tok/sest. | 466 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 34.8 GB | 40k | 16tok/sest. | 466 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 16tok/sest. | 460 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 46.5 GB | 65k120k with q8 cache | 12tok/sest. | 344 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 97.0 GB | – | 4tok/sest. | 97 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 103.5 GB | – | 5tok/sest. | 145 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 76.5 GB | – | 2tok/sest. | 183 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 87.1 GB | – | 3tok/sest. | 319 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | 14k23k with q8 cache | 65tok/sest. | 2210 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.0 GB | – | 25tok/sest. | 1047 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 62.2 GB | – | 17tok/sest. | 1278 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.2 GB | 18k34k with q8 cache | 7tok/sest. | 268 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | 15k24k with q8 cache | 76tok/sest. | 2521 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 61.1 GB | 19k35k with q8 cache | 3tok/sest. | 121 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | offload | 72.2 GB | – | 4tok/sest. | 244 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 78.6 GB | – | 3tok/sest. | 234 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 61.1 GB | 19k35k with q8 cache | 3tok/sest. | 121 tok/s | – |
| MiniMax M2.5 MiniMax | MXFP4 | offload | 132.2 GB | – | 2tok/sest. | 270 tok/s | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | offload | 152.5 GB | – | 2tok/sest. | 74 tok/s | – |
| MiniMax M2 MiniMax | Q4_K_M | offload | 145.8 GB | – | 2tok/sest. | 261 tok/s | – |
| MiniMax M2.1 MiniMax | Q4_K_M | offload | 145.8 GB | – | 2tok/sest. | 261 tok/s | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | offload | 161.3 GB | – | 2tok/sest. | 72 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 93.2 GB | – | 1tok/sest. | 56 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | offload | 147.2 GB | – | 0tok/sest. | 48 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.9 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.8 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.3 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 255.7 GB | – | – | – | – |