NVIDIA RTX PRO 2000 Blackwell
16 GB · 288 GB/s · 70 W
In short
The NVIDIA RTX PRO 2000 Blackwell has 16 GB of GDDR7 memory with 288 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 37 of the 129 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 33 tok/s (estimated). The best new price for the NVIDIA RTX PRO 2000 Blackwell in Germany is 1.000 € at Amazon.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonPNY NVIDIA RTX 2000 Ada Professional Graphics Card 16GB GDDR7 | New | 1.000 € | In stock | 3 h ago | Buy |
| eBayLenovo NVIDIA Grafikkarte RTX PRO 2000 Blackwell 16 GB GDDR7 PCIe 5.0 x8 4 x | New | 1.123 € | In stock | 2 h ago | Buy |
| eBayNVIDIA | New | 1.214 € | In stock | 2 h ago | Buy |
| eBayNVIDIA | New | 1.254 € | In stock | 2 h ago | Buy |
| AmazonPNY Quadro RTX PRO 2000 Blackwell 16GB GDDR7 4xmDP | New | 1.470 € | In stock | 3 h ago | Buy |
| AmazonPNY NVIDIA RTX Pro 2000 Blackwell | New | 1.470 € | In stock | 3 h ago | Buy |
| AmazonNvidia Rtx Pro 2000 Blackwell 16 GB Gddr7 | New | 1.470 € | In stock | 3 h ago | Buy |
| eBayGrafikkarte NVIDIA RTX PRO 2000 Blackwell 16GB PCIe 5.0 x8 Retail | New | 1.484 €+ 6 € delivery | In stock | 2 h ago | Buy |
| eBayPNY RTX Pro 2000 Blackwell | New | 1.916 €+ 5 € delivery | In stock | 2 h ago | Buy |
| eBayPNY RTX PRO 2000 Blackwell | New | 2.071 €+ 5 € delivery | In stock | 2 h ago | Buy |
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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.9 GB | 116k128k with q8 cache | 33tok/sest. | 659 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.5 GB | 120k193k with q8 cache | 13tok/sest. | 287 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 155k256k with q8 cache | 17tok/sest. | 357 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 14.3 GB | 38k40k with q8 cache | 12tok/sest. | 178 tok/s | chat |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 14.8 GB | 35k64k with q8 cache | 12tok/sest. | 198 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.5 GB | 44k81k with q8 cache | 13tok/sest. | 294 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.5 GB | 40k | 13tok/sest. | 294 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 256k | 32tok/sest. | 668 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.5 GB | 45k82k with q8 cache | 13tok/sest. | 284 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.6 GB | 36k67k with q8 cache | 12tok/sest. | 271 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 128k | 20tok/sest. | 449 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 119k125k with q8 cache | 40tok/sest. | 1468 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 65k118k with q8 cache | 16tok/sest. | 311 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.8 GB | 32k | 191tok/sest. | 3197 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 145tok/sest. | 3003 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 96tok/sest. | 1432 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.0 GB | 256k | 79tok/sest. | 1782 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.5 GB | 128k | 63tok/sest. | 1203 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.7 GB | 128k | 44tok/sest. | 718 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.9 GB | 288k482k with q8 cache | 42tok/sest. | 705 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.4 GB | 128k | 37tok/sest. | 814 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.4 GB | 32k | 37tok/sest. | 746 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | fits | 11.7 GB | 128k | 36tok/sest. | 796 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.4 GB | 128k | 34tok/sest. | 1060 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.2 GB | 256k | 31tok/sest. | 668 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-6bit | fits | 14.7 GB | 51k84k with q8 cache | 30tok/sest. | 670 tok/s | chat, coding, agents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.8 GB | 128k | 28tok/sest. | 521 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.0 GB | 128k | 27tok/sest. | 546 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.5 GB | 105k188k with q8 cache | 25tok/sest. | 522 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.8 GB | 32k | 19tok/sest. | 259 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.2 GB | 118k128k with q8 cache | 18tok/sest. | 351 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.5 GB | 119k128k with q8 cache | 16tok/sest. | 245 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.8 GB | 51k93k with q8 cache | 14tok/sest. | 311 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.1 GB | 64k | 14tok/sest. | 245 tok/s | – |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.5 GB | 45k82k with q8 cache | 13tok/sest. | 284 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q5_K_M | fits | 14.8 GB | 35k64k with q8 cache | 12tok/sest. | 198 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | fits | 15.3 GB | 32k60k with q8 cache | 12tok/sest. | 168 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.4 GB | – | 7tok/sest. | 111 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.7 GB | – | 10tok/sest. | 179 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 18.7 GB | – | 7tok/sest. | 110 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.2 GB | – | 5tok/sest. | 91 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.0 GB | – | 14tok/sest. | 202 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.8 GB | – | 25tok/sest. | 721 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 18.6 GB | – | 7tok/sest. | 110 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.1 GB | – | 25tok/sest. | 735 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.1 GB | – | 24tok/sest. | 716 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 19.6 GB | – | 15tok/sest. | 399 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 114 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.7 GB | – | 25tok/sest. | 804 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 24tok/sest. | 538 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 13tok/sest. | 337 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.3 GB | – | 3tok/sest. | 56 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 19.2 GB | – | 6tok/sest. | 115 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 114 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.4 GB | – | 3tok/sest. | 64 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.4 GB | 16k | 11tok/sest. | 179 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 17.7 GB | 4k8k with q8 cache | 21tok/sest. | 751 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.5 GB | – | 8tok/sest. | 110 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 116 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 116 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 116 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.2 GB | 8k15k with q8 cache | 6tok/sest. | 114 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 22.3 GB | – | 5tok/sest. | 100 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 25.7 GB | – | 3tok/sest. | 76 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.8 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.8 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.2 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.5 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.0 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 65.9 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.2 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.6 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.5 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.0 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 70.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 123.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX PRO 2000 Blackwell
- Memory
- 16 GB GDDR7
- Memory bus
- 128-bit
- Memory bandwidth
- 288 GB/s
- FP16 compute
- 17.03 TFLOPS
- Software
- CUDA
- Board power
- 70 W
- PCIe generation
- Gen 5
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA RTX PRO 2000 Blackwell have for AI models?
- The NVIDIA RTX PRO 2000 Blackwell has 16 GB of GDDR7 memory with 288 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX PRO 2000 Blackwell can run locally?
- gpt-oss 20B (MXFP4) fits fully in its memory at 32k context and generates at about 33 tok/s, an estimate from its memory bandwidth. 37 of the 129 models we track fit at that context.
- Can the NVIDIA RTX PRO 2000 Blackwell run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA RTX PRO 2000 Blackwell and system RAM can hold.
- How much does the NVIDIA RTX PRO 2000 Blackwell cost in Germany?
- The best new price for the NVIDIA RTX PRO 2000 Blackwell in Germany is 1.000 € at Amazon.
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.