NVIDIA RTX PRO 6000 Blackwell
96 GB · 1,792 GB/s · 600 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 88.4 GB | 256k | 20tok/sest. | 1592 tok/s | chat, coding, long documents |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 36.6 GB | 256k | 29tok/sest. | 2789 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 89.8 GB | 256k | 62tok/sest. | 4955 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.2 GB | 256k | 30tok/sest. | 2789 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 83.5 GB | 256k | 90tok/sest. | 10991 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 65.0 GB | 128k | 84tok/sest. | 7348 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q4_K_M | fits | 79.5 GB | 256k | 72tok/sest. | 6959 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 42.6 GB | 256k | 25tok/sest. | 2647 tok/s | chat, coding, agents, long documents |
| Mistral Small 4 119B Mistral AI | UD-Q5_K_M | fits | 87.3 GB | 419k665k with q8 cache | 80tok/sest. | 4297 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.4 GB | 256k | 114tok/sest. | 13551 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.2 GB | 256k | 30tok/sest. | 2789 tok/s | chat, coding, agents, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.2 GB | 256k | 95tok/sest. | 16449 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q4_K_M | fits | 92.4 GB | 128k | 19tok/sest. | 1244 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.4 GB | 256k | 114tok/sest. | 13551 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 83.5 GB | 256k | 104tok/sest. | 12010 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 37.7 GB | 198k | 54tok/sest. | 6392 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 44.8 GB | 384k | 24tok/sest. | 2493 tok/s | chat, coding, agents, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.8 GB | 256k | 160tok/sest. | 18228 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.1 GB | 1024k | 155tok/sest. | 10167 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.7 GB | 128k | 118tok/sest. | 10650 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 43.7 GB | 256k | 42tok/sest. | 3942 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 65.9 GB | 40k | 16tok/sest. | 1117 tok/s | chat, coding, long documents |
| Gemma 4 12B | Q8_0 | fits | 15.6 GB | 256k | 73tok/sest. | 6835 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.4 GB | 256k | 80tok/sest. | 8130 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 38.6 GB | 128k | 28tok/sest. | 3412 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 44.8 GB | 128k | 24tok/sest. | 2493 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 65.9 GB | 128k | 16tok/sest. | 1498 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q5_K_M | fits | 88.0 GB | 128k | 12tok/sest. | 725 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 34.8 GB | 256k | 31tok/sest. | 3202 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 40k | 30tok/sest. | 2725 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.6 GB | 128k | 40tok/sest. | 4121 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.6 GB | 40k | 40tok/sest. | 4121 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.0 GB | 16k | 26tok/sest. | 2732 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 256k | 126tok/sest. | 12664 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 26.9 GB | 256k | 41tok/sest. | 4174 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.2 GB | 128k | 36tok/sest. | 3747 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 12.6 GB | 128k | 93tok/sest. | 11399 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.8 GB | 125k | 89tok/sest. | 15237 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 23.6 GB | 128k | 47tok/sest. | 4498 tok/s | chat, coding, long documents |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 102.4 GB | 50k89k with q8 cache | 15tok/sest. | 530 tok/s | chat, coding, agents, long documents |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 104.2 GB | – | 24tok/sest. | 882 tok/s | chat, coding, agents, long documents |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 102.6 GB | 99k182k with q8 cache | 8tok/sest. | 1781 tok/s | chat, coding, agents |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX PRO 6000 Blackwell
- Memory
- 96 GB GDDR7
- Memory bus
- 512-bit
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 504 TFLOPS
- Software
- CUDA
- Board power
- 600 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16