RTX 5090 32GB
$6,984
Parts
Compatibility: No problems found.Est. load 820 W of 1200 W · spikes to 1165 W
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 5090 32 GB · 1792 GB/s · 575 W | $4,921 | eBay | Buy |
| CPU | AMD Ryzen 9 9950X AM5 · 16 cores · 24 PCIe lanes | $559 | eBay | Buy |
| Motherboard | MSI MPG X870E Carbon WiFi AM5 · DDR5 · ATX | $370 | eBay | Buy |
| Memory | Kingston Fury Beast 96GB (2×48GB) DDR5-6400 96 GB · DDR5-6400 | Not sold now | – | |
| Power supply | Seasonic Vertex GX-1200 1200W 1200 W · ATX 3 | $324 | eBay | Buy |
| Case | Lian Li O11 Dynamic EVO GPUs up to 426 mm | $140 | eBay | Buy |
| Storage | WD Black SN850X 4TB 4000 GB NVME | $670 | eBay | Buy |
| Total + 1 without a price | $6,984 | |||
- Note: Check the power connectors on the card you buy: this power supply has 1 12V-2x6 and 3 8-pin PCIe connectors.
- Note: Lian Li O11 Dynamic EVO fits graphics cards up to 426 mm: check the length of the card you buy.
What this build runs
The most precise quant that fits, at 128k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 30.1 GB | 147k256k with q8 cache | 36tok/sest. | 1156 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 30.6 GB | 140k245k with q8 cache | 36tok/sest. | 1156 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q4_K_M | fits | 29.3 GB | 153k256k with q8 cache | 37tok/sest. | 1097 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 31.3 GB | 131k206k with q8 cache | 128tok/sest. | 5619 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 30.5 GB | 141k246k with q8 cache | 36tok/sest. | 1156 tok/s | chat, coding, agents, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.2 GB | 216k256k with q8 cache | 95tok/sest. | 6821 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 30.9 GB | 148k232k with q8 cache | 129tok/sest. | 5619 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 31.1 GB | 133k198k with q8 cache | 60tok/sest. | 2651 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.5 GB | 196k267k with q8 cache | 227tok/sest. | 4216 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.7 GB | 128k | 118tok/sest. | 4416 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | fits | 30.7 GB | 134k241k with q8 cache | 45tok/sest. | 1635 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 15.6 GB | 256k | 73tok/sest. | 2835 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.4 GB | 256k | 80tok/sest. | 3371 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q5_K_M | fits | 29.8 GB | 128k | 37tok/sest. | 1415 tok/s | chat, coding, long documents |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 30.4 GB | 134k244k with q8 cache | 36tok/sest. | 1328 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q5_K_M | fits | 31.2 GB | 40k | 35tok/sest. | 1130 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.6 GB | 128k | 40tok/sest. | 1709 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.6 GB | 40k | 40tok/sest. | 1709 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 256k | 126tok/sest. | 5251 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 26.9 GB | 160k256k with q8 cache | 41tok/sest. | 1731 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.2 GB | 128k | 36tok/sest. | 1554 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 12.6 GB | 128k | 93tok/sest. | 4727 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.8 GB | 125k | 89tok/sest. | 6319 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 23.6 GB | 128k | 47tok/sest. | 1865 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.4 GB | 32k | 519tok/sest. | 14196 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.7 GB | 256k | 455tok/sest. | 18931 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.3 GB | 256k | 363tok/sest. | 12105 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.7 GB | 128k | 197tok/sest. | 6343 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.3 GB | 128k | 146tok/sest. | 7309 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.2 GB | 128k | 134tok/sest. | 3410 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.6 GB | 128k | 102tok/sest. | 4374 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.6 GB | 32k | 102tok/sest. | 4208 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.8 GB | 128k | 91tok/sest. | 4589 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.8 GB | 128k | 77tok/sest. | 2700 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.1 GB | 128k | 76tok/sest. | 2753 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.8 GB | 128k | 72tok/sest. | 1480 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.0 GB | 128k | 71tok/sest. | 2264 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.4 GB | 64k | 65tok/sest. | 1480 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q6_K | fits | 31.2 GB | 128k | 53tok/sest. | 3692 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 25.4 GB | 128k | 43tok/sest. | 1865 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 26.9 GB | 160k256k with q8 cache | 41tok/sest. | 1731 tok/s | chat, coding, agents, long documents |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 102.4 GB | – | 3tok/sest. | 133 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 104.2 GB | – | 5tok/sest. | 222 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 78.0 GB | – | 2tok/sest. | 419 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 102.6 GB | – | 1tok/sest. | 446 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 43.6 GB | – | 17tok/sest. | 1699 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 49.7 GB | – | 16tok/sest. | 3520 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.5 GB | – | 12tok/sest. | 2151 tok/s | chat |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 64.4 GB | – | 8tok/sest. | 2089 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 41.7 GB | – | 23tok/sest. | 1508 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 66.7 GB | – | 2tok/sest. | 349 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 49.7 GB | – | 18tok/sest. | 3847 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 107k195k with q8 cache | 11tok/sest. | 971 tok/s | chat, coding, agents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.8 GB | – | 58tok/sest. | 7091 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 51.9 GB | 40k | 3tok/sest. | 351 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 107k128k with q8 cache | 11tok/sest. | 971 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 51.9 GB | 47k88k with q8 cache | 3tok/sest. | 470 tok/s | chat, coding |
| Llama 3.3 70B Meta | Q4_K_M | offload | 81.1 GB | – | 1tok/sest. | 188 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.7 GB | 16k | 12tok/sest. | 1065 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 33.8 GB | 115k128k with q8 cache | 14tok/sest. | 956 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | 107k128k with q8 cache | 11tok/sest. | 980 tok/s | chat, coding, agents |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 34.8 GB | 40k | 11tok/sest. | 980 tok/s | chat, coding |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | 40k | 11tok/sest. | 980 tok/s | chat, coding, agents |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 34.8 GB | 107k128k with q8 cache | 11tok/sest. | 971 tok/s | chat, coding, agents |
| granite 4.2 30b IBM | Q4_K_M | offload | 50.2 GB | 54k100k with q8 cache | 3tok/sest. | 568 tok/s | chat, coding, agents |
| GLM 4.5V Z.ai | Q4_K_M | offload | 83.7 GB | – | 2tok/sest. | 329 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 90.1 GB | – | 2tok/sest. | 321 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 81.1 GB | – | 1tok/sest. | 188 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 115.2 GB | – | 1tok/sest. | 97 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.2 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.8 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.6 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 169.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.7 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.7 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.2 GB | – | – | – | – |