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 8k context it runs 44 of the 129 open models we track fully in memory; the most capable is Devstral Small 2 24B at Q4_K_M, at about 11 tok/s (estimated). The best new price for the NVIDIA RTX PRO 2000 Blackwell in the US is $1,580 at eBay; used, it starts at $1,439 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayPNY NVIDIA RTX PRO 2000 Blackwell Single Fan 16GB GDDR7 PCIe 5.0 Grap | used, asking price | $1,439 | In stock | 5 h ago | Buy |
| eBayNEW NVIDIA RTX PRO 2000 BLACKWELL 16GB Graphics Card | New | $1,580 | In stock | 5 h ago | Buy |
| eBayPNY VCNRTXPRO2000B-PB NVIDIA RTX PRO 2000 Blackwell 16GB GDDR7 GPU Graphic Card | New | $1,600+ $4 delivery | In stock | 5 h ago | Buy |
| eBayPNY VCNRTXPRO2000B-B NVIDIA RTX PRO 2000 Blackwell 16GB GDDR7 Workstation GPU | New | $2,013 | In stock | 5 h ago | Buy |
| eBayPNY VCNRTXPRO2000B-PB NVIDIA RTX PRO 2000 Blackwell 16GB GDDR7 Workstation GPU | New | $2,025 | In stock | 5 h ago | Buy |
| eBayPNY VCNRTXPRO2000B-PB NVIDIA RTX PRO 2000 Blackwell Graphic Card | New | $2,210 | In stock | 5 h ago | Buy |
| eBayPNY VCNRTXPRO2000B-PB NVIDIA RTX PRO 2000 Blackwell 16GB GDDR7 GPU Graphic Card | New | $2,233 | In stock | 5 h ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Devstral Small 2 24B Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 151 tok/s | – |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 116k128k with q8 cache | 41tok/sest. | 832 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 120k193k with q8 cache | 14tok/sest. | 305 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 155k256k with q8 cache | 18tok/sest. | 386 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 151 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 13.3 GB | 21k38k with q8 cache | 13tok/sest. | 233 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 8k14k with q8 cache | 11tok/sest. | 251 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 44k81k with q8 cache | 18tok/sest. | 408 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 18tok/sest. | 408 tok/s | chat |
| Phi-4 14B Microsoft | Q6_K | fits | 13.5 GB | 16k | 13tok/sest. | 235 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 37tok/sest. | 778 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 45k82k with q8 cache | 18tok/sest. | 381 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 36k67k with q8 cache | 17tok/sest. | 378 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 21tok/sest. | 468 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 119k125k with q8 cache | 73tok/sest. | 2732 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 65k118k with q8 cache | 23tok/sest. | 421 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 283tok/sest. | 5717 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 192tok/sest. | 3934 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 115tok/sest. | 1614 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 2.6 GB | 256k | 91tok/sest. | 2073 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 84tok/sest. | 1799 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 59tok/sest. | 1190 tok/s | chat, coding, agents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 53tok/sest. | 1197 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 53tok/sest. | 1057 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 288k482k with q8 cache | 53tok/sest. | 846 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | fits | 10.8 GB | 128k | 49tok/sest. | 1110 tok/s | chat, coding, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 42tok/sest. | 792 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 105k188k with q8 cache | 40tok/sest. | 812 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 39tok/sest. | 852 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-6bit | fits | 13.9 GB | 51k84k with q8 cache | 39tok/sest. | 1041 tok/s | chat, coding, agents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 38tok/sest. | 1316 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 256k | 36tok/sest. | 778 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 118k128k with q8 cache | 21tok/sest. | 454 tok/s | chat |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.7 GB | 32k | 21tok/sest. | 357 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 51k93k with q8 cache | 19tok/sest. | 421 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 45k82k with q8 cache | 18tok/sest. | 381 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 119k128k with q8 cache | 17tok/sest. | 329 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 15tok/sest. | 329 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q6_K | fits | 13.5 GB | 17k32k with q8 cache | 13tok/sest. | 228 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 154 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 154 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 154 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | fits | 15.3 GB | 8k15k with q8 cache | 11tok/sest. | 151 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.4 GB | 8k14k with q8 cache | 11tok/sest. | 251 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 16.7 GB | – | 9tok/sest. | 127 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.0 GB | – | 12tok/sest. | 221 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 17.0 GB | – | 8tok/sest. | 126 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 19.2 GB | – | 6tok/sest. | 102 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.4 GB | – | 17tok/sest. | 294 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.2 GB | – | 32tok/sest. | 954 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 17.0 GB | – | 8tok/sest. | 126 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 16.5 GB | – | 31tok/sest. | 838 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 21.5 GB | – | 31tok/sest. | 947 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 18.2 GB | – | 22tok/sest. | 581 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.5 GB | – | 27tok/sest. | 964 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 18.8 GB | – | 28tok/sest. | 738 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 28.8 GB | – | 26tok/sest. | 778 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 5tok/sest. | 86 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 17.2 GB | – | 8tok/sest. | 127 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 21.2 GB | – | 5tok/sest. | 90 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 15.7 GB | 4k8k with q8 cache | 53tok/sest. | 1419 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.0 GB | – | 8tok/sest. | 117 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 19.5 GB | – | 6tok/sest. | 106 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 20.6 GB | – | 5tok/sest. | 113 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.8 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 51.9 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.5 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 44.4 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 42.8 GB | – | – | – | – |
| 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 R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 42.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 377.9 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 V3.1 Terminus DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 73.3 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.4 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.4 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 67.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 383.8 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 Dev 72B Moonshot AI | Q6_K | won't run | 63.2 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 | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.4 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.3 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?
- Devstral Small 2 24B (Q4_K_M) fits fully in its memory at 8k context and generates at about 11 tok/s, an estimate from its memory bandwidth. 44 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 92 GB at 8k 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 the US?
- The best new price for the NVIDIA RTX PRO 2000 Blackwell in the US is $1,580 at eBay; used, it starts at $1,439 (asking price).
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.