NVIDIA RTX PRO 5000 Blackwell 48GB
48 GB · 1,344 GB/s · 300 W
In short
The NVIDIA RTX PRO 5000 Blackwell 48GB has 48 GB of GDDR7 memory with 1,344 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 78 of the 125 open models we track fully in memory; the most capable is DeepSeek V4 Flash at UD-Q2_K_XL, at about 67 tok/s (estimated). We have no current price for the NVIDIA RTX PRO 5000 Blackwell 48GB 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.
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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 92.0 GB | 39k69k with q8 cache | 67tok/sest. | 519 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 85.2 GB | 256k | 16tok/sest. | 267 tok/s | chat |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 73.2 GB | 95k175k with q8 cache | 88tok/sest. | 1172 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 256k | 28tok/sest. | 580 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 86.7 GB | 256k | 65tok/sest. | 1535 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 29tok/sest. | 580 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 60.5 GB | 128k | 146tok/sest. | 2602 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.4 GB | 256k | 114tok/sest. | 3876 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 91.3 GB | 256k | 52tok/sest. | 1352 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.9 GB | 256k | 24tok/sest. | 506 tok/s | chat, coding, long documents |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 93.9 GB | 39k62k with q8 cache | 82tok/sest. | 2005 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 151tok/sest. | 4971 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 29tok/sest. | 580 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 256k | 110tok/sest. | 3788 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q6_K | fits | 94.8 GB | 8k14k with q8 cache | 36tok/sest. | 915 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 151tok/sest. | 4971 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 80.4 GB | 256k | 147tok/sest. | 4873 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 31.2 GB | 198k | 87tok/sest. | 2782 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 384k | 32tok/sest. | 654 tok/s | chat, coding, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.8 GB | 256k | 146tok/sest. | 5179 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 190tok/sest. | 3598 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.9 GB | 1024k | 152tok/sest. | 4724 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 32.1 GB | 256k | 125tok/sest. | 3596 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.6 GB | 40k | 23tok/sest. | 447 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 63tok/sest. | 1320 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 85tok/sest. | 1671 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 32tok/sest. | 654 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 128k | 28tok/sest. | 588 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.6 GB | 128k | 23tok/sest. | 468 tok/s | chat |
| Llama 3.3 70B Meta | Q8_0 | fits | 73.5 GB | 74k128k with q8 cache | 11tok/sest. | 218 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 256k | 53tok/sest. | 1085 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 49tok/sest. | 1008 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 84tok/sest. | 1764 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 84tok/sest. | 1764 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 48tok/sest. | 1015 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 174tok/sest. | 3364 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 82tok/sest. | 1648 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 78tok/sest. | 1636 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 98tok/sest. | 2025 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 341tok/sest. | 11821 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 109tok/sest. | 1821 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 1319tok/sest. | 24740 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 895tok/sest. | 17021 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 536tok/sest. | 6982 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.1 GB | 128k | 391tok/sest. | 7786 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.0 GB | 128k | 275tok/sest. | 5147 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.3 GB | 128k | 247tok/sest. | 5181 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.3 GB | 32k | 247tok/sest. | 4572 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.3 GB | 1024k | 245tok/sest. | 3662 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 5.1 GB | 128k | 194tok/sest. | 3429 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.4 GB | 256k | 184tok/sest. | 3512 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.4 GB | 128k | 183tok/sest. | 3686 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.5 GB | 128k | 179tok/sest. | 6207 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 128k | 177tok/sest. | 5696 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.7 GB | 256k | 169tok/sest. | 3364 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 17.2 GB | 128k | 149tok/sest. | 4802 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.0 GB | 128k | 142tok/sest. | 4802 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 9.1 GB | 128k | 97tok/sest. | 1965 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.1 GB | 32k | 97tok/sest. | 1543 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 87tok/sest. | 1821 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 82tok/sest. | 1648 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.8 GB | 128k | 81tok/sest. | 1425 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.4 GB | 64k | 69tok/sest. | 1425 tok/s | chat, coding, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.8 GB | 256k | 53tok/sest. | 1085 tok/s | chat, coding, agents, long documents |
| GLM 4.5V Z.ai | Q4_K_M | fits | 61.8 GB | 64k | 50tok/sest. | 877 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 17.3 GB | 128k | 48tok/sest. | 988 tok/s | chat, coding, long documents |
| GLM 4.6V Z.ai | Q4_K_M | fits | 68.2 GB | 128k | 46tok/sest. | 877 tok/s | chat, coding, agents |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 21.0 GB | 256k | 39tok/sest. | 580 tok/s | chat, coding, agents, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 32tok/sest. | 666 tok/s | chat, coding, long documents |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 32tok/sest. | 666 tok/s | chat, coding, long documents |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 32tok/sest. | 666 tok/s | chat, coding, long documents |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 32tok/sest. | 654 tok/s | chat, coding, long documents |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.4 GB | 128k | 26tok/sest. | 537 tok/s | chat, coding, long documents |
| granite 4.2 30b IBM | Q8_0 | fits | 32.1 GB | 128k | 25tok/sest. | 528 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 73.5 GB | 74k128k with q8 cache | 11tok/sest. | 218 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q8_0 | fits | 75.6 GB | 68k126k with q8 cache | 10tok/sest. | 212 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q5_K_M | fits | 86.1 GB | 32k60k with q8 cache | 9tok/sest. | 124 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q5_K_M | fits | 86.1 GB | 32k60k with q8 cache | 9tok/sest. | 121 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 102.6 GB | – | 27tok/sest. | 503 tok/s | chat, coding |
| MiniMax M2.5 MiniMax | MXFP4 | offload | 118.4 GB | – | 16tok/sest. | 1029 tok/s | chat |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 156.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 384.2 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.8 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.7 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 748.2 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX PRO 5000 Blackwell 48GB
- Memory
- 48 GB GDDR7
- Memory bus
- 384-bit
- Memory bandwidth
- 1,344 GB/s
- FP16 compute
- 73.69 TFLOPS
- Software
- CUDA
- Board power
- 300 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA RTX PRO 5000 Blackwell 48GB have for AI models?
- The NVIDIA RTX PRO 5000 Blackwell 48GB has 48 GB of GDDR7 memory with 1,344 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX PRO 5000 Blackwell 48GB can run locally?
- DeepSeek V4 Flash (UD-Q2_K_XL) fits fully in its memory at 8k context and generates at about 67 tok/s, an estimate from its memory bandwidth. 78 of the 125 models we track fit at that context.
- Can the NVIDIA RTX PRO 5000 Blackwell 48GB run GLM 5.3 Flash?
- Not fully in memory: at UD-Q2_K_XL and 8k context GLM 5.3 Flash needs about 103 GB, so part of it runs from system RAM and it slows to about 27 tok/s (estimated).
- How much does the NVIDIA RTX PRO 5000 Blackwell 48GB cost in the US?
- We have no current price for the NVIDIA RTX PRO 5000 Blackwell 48GB in the US.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.