RTX PRO 6000 96GB workstation
$20,424
Parts
Compatibility: No problems found.Est. load 1025 W of 1500 W · spikes to 1385 W
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| GPU | NVIDIA RTX PRO 6000 Blackwell 96 GB · 1792 GB/s · 600 W | $17,400 | eBay | Buy |
| CPU | AMD Ryzen Threadripper 7960X sTR5 · 24 cores · 88 PCIe lanes | $985 | eBay | Buy |
| Motherboard | ASUS Pro WS TRX50-SAGE WiFi sTR5 · DDR5 · E-ATX | $800 | eBay | Buy |
| Memory | Kingston Server Premier 256GB (4×64GB) DDR5-5600 RDIMM 256 GB · DDR5-5600 | Not sold now | – | |
| Power supply | Corsair HX1500i ATX 3.1 1500W 1500 W · ATX 3 | $350 | eBay | Buy |
| Case | Phanteks Enthoo Pro 2 GPUs up to 503 mm | $219 | eBay | Buy |
| Storage | WD Black SN850X 4TB 4000 GB NVME | $670 | eBay | Buy |
| Total + 1 without a price | $20,424 | |||
- Note: Check the power connectors on the card you buy: this power supply has 2 12V-2x6 and 5 8-pin PCIe connectors.
- Note: Phanteks Enthoo Pro 2 fits graphics cards up to 503 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 |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 91.6 GB | 50k89k with q8 cache | 89tok/sest. | 3549 tok/s | chat, coding, agents, long documents |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 84.8 GB | 256k | 21tok/sest. | 1824 tok/s | chat, coding, long documents |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 72.8 GB | 99k182k with q8 cache | 117tok/sest. | 8014 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 37tok/sest. | 3967 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 95.1 GB | 16k26k with q8 cache | 79tok/sest. | 10495 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 38tok/sest. | 3967 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 60.1 GB | 128k | 195tok/sest. | 17793 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 151tok/sest. | 26510 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 90.9 GB | 256k | 69tok/sest. | 9243 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.5 GB | 256k | 33tok/sest. | 3459 tok/s | chat, coding, agents, long documents |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 93.5 GB | 75k119k with q8 cache | 110tok/sest. | 13714 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 201tok/sest. | 33997 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 38tok/sest. | 3967 tok/s | chat, coding, agents, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.1 GB | 256k | 147tok/sest. | 25905 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q6_K | fits | 94.4 GB | 13k24k with q8 cache | 40tok/sest. | 5233 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 201tok/sest. | 33997 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 196tok/sest. | 33327 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.8 GB | 198k | 117tok/sest. | 19026 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 384k | 42tok/sest. | 4473 tok/s | chat, coding, agents, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.4 GB | 256k | 195tok/sest. | 35423 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 253tok/sest. | 24607 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.5 GB | 1024k | 202tok/sest. | 32311 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 256k | 167tok/sest. | 24595 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 40k | 30tok/sest. | 3060 tok/s | chat, coding, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 85tok/sest. | 9026 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 113tok/sest. | 11430 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 42tok/sest. | 4473 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 28.5 GB | 128k | 37tok/sest. | 4021 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.2 GB | 128k | 30tok/sest. | 3199 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q8_0 | fits | 73.1 GB | 78k128k with q8 cache | 14tok/sest. | 1494 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 256k | 71tok/sest. | 7418 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 65tok/sest. | 6895 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 128k | 112tok/sest. | 12066 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 112tok/sest. | 12066 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 64tok/sest. | 6941 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 231tok/sest. | 23010 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 109tok/sest. | 11274 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 128k | 104tok/sest. | 11190 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 131tok/sest. | 13851 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 455tok/sest. | 80847 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 128k | 145tok/sest. | 12456 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 1759tok/sest. | 169205 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 1193tok/sest. | 116415 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 715tok/sest. | 47753 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 522tok/sest. | 53254 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 366tok/sest. | 35202 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 329tok/sest. | 35432 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 329tok/sest. | 31267 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 259tok/sest. | 23449 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 243tok/sest. | 25208 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.1 GB | 128k | 238tok/sest. | 42455 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 236tok/sest. | 38955 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 190tok/sest. | 32841 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 130tok/sest. | 13440 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 128k | 116tok/sest. | 12456 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 109tok/sest. | 11274 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 108tok/sest. | 9747 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 92tok/sest. | 9747 tok/s | chat, coding, long documents |
| GLM 4.5V Z.ai | Q4_K_M | fits | 61.4 GB | 64k | 67tok/sest. | 5996 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 128k | 64tok/sest. | 6757 tok/s | chat, coding, long documents |
| GLM 4.6V Z.ai | Q4_K_M | fits | 67.8 GB | 128k | 61tok/sest. | 5996 tok/s | chat, coding, agents, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 42tok/sest. | 4552 tok/s | chat, coding, agents, long documents |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 42tok/sest. | 4552 tok/s | chat, coding, long documents |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 42tok/sest. | 4552 tok/s | chat, coding, agents, long documents |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 42tok/sest. | 4473 tok/s | chat, coding, agents, long documents |
| granite 4.2 30b IBM | Q8_0 | fits | 31.7 GB | 128k | 33tok/sest. | 3609 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 73.1 GB | 78k128k with q8 cache | 14tok/sest. | 1494 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q5_K_M | fits | 85.7 GB | 35k66k with q8 cache | 12tok/sest. | 830 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 102.2 GB | – | 46tok/sest. | 3464 tok/s | chat, coding, agents, long documents |
| MiniMax M2.5 MiniMax | MXFP4 | offload | 118.0 GB | – | 30tok/sest. | 7081 tok/s | chat |
| MiniMax M2 MiniMax | Q4_K_M | offload | 131.5 GB | – | 21tok/sest. | 6685 tok/s | chat |
| MiniMax M2.1 MiniMax | Q4_K_M | offload | 131.5 GB | – | 21tok/sest. | 6685 tok/s | chat |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | offload | 147.1 GB | – | 9tok/sest. | 1978 tok/s | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | offload | 155.8 GB | – | 8tok/sest. | 1903 tok/s | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | offload | 248.4 GB | – | 6tok/sest. | 2641 tok/s | – |
| GLM 4.7 Z.ai | Q4_K_M | offload | 205.2 GB | – | 4tok/sest. | 1587 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | offload | 127.2 GB | – | 2tok/sest. | 719 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |