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 64k context it runs 59 of the 129 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q6_K, at about 6 tok/s (estimated). We have no current price for the NVIDIA RTX PRO 2000 Blackwell in the US.
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.
No retailer in this market lists it right now.
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q6_K | fits | 27.8 GB | 107k187k with q8 cache | 6tok/sest. | 112 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.6 GB | 125k219k with q8 cache | 7tok/sest. | 112 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 30.7 GB | 64k122k with q8 cache | 6tok/sest. | 102 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 30.1 GB | 92k144k with q8 cache | 28tok/sest. | 674 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.5 GB | 126k221k with q8 cache | 7tok/sest. | 112 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.9 GB | 176k256k with q8 cache | 19tok/sest. | 690 tok/s | chat, coding, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.7 GB | 109k170k with q8 cache | 28tok/sest. | 674 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 27.8 GB | 116k198k with q8 cache | 14tok/sest. | 334 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.5 GB | 72k131k with q8 cache | 6tok/sest. | 110 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 30.0 GB | 129k168k with q8 cache | 32tok/sest. | 831 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.0 GB | 122k167k with q8 cache | 45tok/sest. | 541 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 27tok/sest. | 516 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 27.7 GB | 95k170k with q8 cache | 13tok/sest. | 241 tok/s | chat, coding |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 13tok/sest. | 265 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 15tok/sest. | 325 tok/s | chat |
| Gemma 3 27B | Q6_K | fits | 27.5 GB | 102k128k with q8 cache | 6tok/sest. | 125 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.5 GB | 72k128k with q8 cache | 6tok/sest. | 110 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.8 GB | 100k183k with q8 cache | 7tok/sest. | 155 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.1 GB | 40k | 7tok/sest. | 136 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 128k | 10tok/sest. | 215 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 10tok/sest. | 215 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.5 GB | 16k | 6tok/sest. | 137 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 27tok/sest. | 563 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 153k256k with q8 cache | 10tok/sest. | 212 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 128k | 9tok/sest. | 196 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 18tok/sest. | 425 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 25tok/sest. | 908 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 128k | 12tok/sest. | 231 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 32k | 134tok/sest. | 2013 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.0 GB | 256k | 109tok/sest. | 2283 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.6 GB | 256k | 79tok/sest. | 1244 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 4.0 GB | 256k | 67tok/sest. | 1501 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.0 GB | 128k | 47tok/sest. | 834 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.6 GB | 128k | 33tok/sest. | 470 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.6 GB | 653k1024k with q8 cache | 32tok/sest. | 577 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.4 GB | 128k | 29tok/sest. | 841 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.8 GB | 256k | 26tok/sest. | 563 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.9 GB | 128k | 26tok/sest. | 570 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.9 GB | 32k | 26tok/sest. | 536 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 19.2 GB | 128k | 21tok/sest. | 579 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.0 GB | 128k | 20tok/sest. | 454 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.8 GB | 128k | 20tok/sest. | 358 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 10.1 GB | 128k | 19tok/sest. | 370 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.4 GB | 244k256k with q8 cache | 17tok/sest. | 354 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.7 GB | 32k | 16tok/sest. | 190 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.5 GB | 128k | 15tok/sest. | 270 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 30.2 GB | 70k125k with q8 cache | 14tok/sest. | 520 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.3 GB | 128k | 14tok/sest. | 182 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.9 GB | 64k | 12tok/sest. | 182 tok/s | – |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.4 GB | 128k | 10tok/sest. | 231 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.4 GB | 153k256k with q8 cache | 10tok/sest. | 212 tok/s | chat |
| Muse Glimmer 30B meta-models | Q6_K | fits | 24.2 GB | 128k | 7tok/sest. | 113 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 24.8 GB | 100k183k with q8 cache | 7tok/sest. | 155 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 24.9 GB | 150k256k with q8 cache | 7tok/sest. | 112 tok/s | – |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 27.1 GB | 86k128k with q8 cache | 7tok/sest. | 112 tok/s | – |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 27.1 GB | 40k | 7tok/sest. | 112 tok/s | – |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 27.1 GB | 86k128k with q8 cache | 7tok/sest. | 110 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 28.1 GB | 77k128k with q8 cache | 6tok/sest. | 124 tok/s | – |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 29.5 GB | 40k | 6tok/sest. | 112 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.1 GB | – | 13tok/sest. | 194 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 14tok/sest. | 419 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.0 GB | – | 9tok/sest. | 201 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.3 GB | – | 18tok/sest. | 195 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.2 GB | – | 3tok/sest. | 55 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 17tok/sest. | 478 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.9 GB | 40k | 4tok/sest. | 52 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.0 GB | 43k80k with q8 cache | 4tok/sest. | 64 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.3 GB | 50k93k with q8 cache | 4tok/sest. | 77 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.5 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.1 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 62.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.3 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 93.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.9 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.8 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.3 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.2 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.2 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?
- Qwen 3.8 27B (Q6_K) fits fully in its memory at 64k context and generates at about 6 tok/s, an estimate from its memory bandwidth. 59 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 97 GB at 64k 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?
- We have no current price for the NVIDIA RTX PRO 2000 Blackwell in the US.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.