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 32k 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 52 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 94.2 GB | 39k69k with q8 cache | 52tok/sest. | 249 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 85.9 GB | 256k | 16tok/sest. | 259 tok/s | chat |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 79.2 GB | 95k175k with q8 cache | 42tok/sest. | 705 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.5 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 87.4 GB | 256k | 60tok/sest. | 1254 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 61.5 GB | 128k | 115tok/sest. | 2026 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 81.1 GB | 256k | 100tok/sest. | 3023 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 91.7 GB | 256k | 51tok/sest. | 1268 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 35.0 GB | 256k | 23tok/sest. | 477 tok/s | chat, coding, long documents |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 94.6 GB | 39k62k with q8 cache | 75tok/sest. | 1394 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 131tok/sest. | 3818 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.1 GB | 256k | 99tok/sest. | 3397 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q5_K_M | fits | 84.8 GB | 85k128k with q8 cache | 30tok/sest. | 518 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 131tok/sest. | 3818 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 81.1 GB | 256k | 125tok/sest. | 3596 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.6 GB | 198k | 71tok/sest. | 1994 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 384k | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 140tok/sest. | 4357 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.3 GB | 128k | 155tok/sest. | 2851 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.2 GB | 1024k | 143tok/sest. | 3291 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.5 GB | 256k | 78tok/sest. | 1756 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.7 GB | 40k | 19tok/sest. | 332 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.9 GB | 256k | 62tok/sest. | 1240 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.2 GB | 256k | 78tok/sest. | 1546 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 30.9 GB | 128k | 26tok/sest. | 568 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.7 GB | 128k | 19tok/sest. | 381 tok/s | chat |
| Llama 3.3 70B Meta | Q8_0 | fits | 81.1 GB | 74k128k with q8 cache | 10tok/sest. | 180 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.7 GB | 256k | 42tok/sest. | 859 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.9 GB | 40k | 40tok/sest. | 772 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.9 GB | 128k | 62tok/sest. | 1273 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.9 GB | 40k | 62tok/sest. | 1273 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 22.0 GB | 16k | 37tok/sest. | 776 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.5 GB | 256k | 149tok/sest. | 2892 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.9 GB | 256k | 61tok/sest. | 1230 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 15.0 GB | 128k | 57tok/sest. | 1171 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.8 GB | 128k | 91tok/sest. | 1942 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 11.2 GB | 125k | 187tok/sest. | 6351 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.4 GB | 128k | 77tok/sest. | 1345 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.2 GB | 32k | 892tok/sest. | 13832 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.4 GB | 256k | 676tok/sest. | 12993 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.0 GB | 256k | 449tok/sest. | 6194 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.9 GB | 128k | 294tok/sest. | 5204 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 5.1 GB | 128k | 204tok/sest. | 3108 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 5.3 GB | 1024k | 194tok/sest. | 3052 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.8 GB | 128k | 171tok/sest. | 3520 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.8 GB | 32k | 171tok/sest. | 3228 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.8 GB | 128k | 158tok/sest. | 4586 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.6 GB | 256k | 145tok/sest. | 2892 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 7.2 GB | 128k | 132tok/sest. | 2255 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 7.4 GB | 128k | 127tok/sest. | 2364 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 18.0 GB | 128k | 121tok/sest. | 3446 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.8 GB | 128k | 117tok/sest. | 3446 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.9 GB | 256k | 117tok/sest. | 2259 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.5 GB | 128k | 104tok/sest. | 3540 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 10.2 GB | 32k | 87tok/sest. | 1123 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.6 GB | 128k | 84tok/sest. | 1521 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.9 GB | 128k | 74tok/sest. | 1059 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 13.2 GB | 128k | 65tok/sest. | 1345 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.5 GB | 64k | 64tok/sest. | 1059 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.9 GB | 256k | 61tok/sest. | 1230 tok/s | chat, coding, agents, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 19.7 GB | 256k | 42tok/sest. | 859 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.9 GB | 128k | 38tok/sest. | 727 tok/s | chat, coding, long documents |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 22.7 GB | 256k | 36tok/sest. | 535 tok/s | chat, coding, agents, long documents |
| GLM 4.5V Z.ai | Q4_K_M | fits | 66.3 GB | 64k | 34tok/sest. | 505 tok/s | chat, coding, agents |
| GLM 4.6V Z.ai | Q4_K_M | fits | 72.6 GB | 128k | 32tok/sest. | 505 tok/s | chat, coding, agents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.6 GB | 40k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.6 GB | 40k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.9 GB | 128k | 25tok/sest. | 515 tok/s | chat, coding, long documents |
| granite 4.2 30b IBM | Q8_0 | fits | 38.3 GB | 128k | 21tok/sest. | 438 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 81.1 GB | 74k128k with q8 cache | 10tok/sest. | 180 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q8_0 | fits | 83.2 GB | 68k126k with q8 cache | 10tok/sest. | 176 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q5_K_M | fits | 94.5 GB | 32k60k with q8 cache | 8tok/sest. | 103 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q5_K_M | fits | 94.5 GB | 32k60k with q8 cache | 8tok/sest. | 102 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 103.0 GB | – | 25tok/sest. | 319 tok/s | chat, coding |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.6 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 424.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.7 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 32k context and generates at about 52 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 32k context GLM 5.3 Flash needs about 103 GB, so part of it runs from system RAM and it slows to about 25 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 32k context. See the best hardware for local AI at every budget.