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 65 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 27 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 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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.7 GB | 256k | 116tok/sest. | 1254 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.7 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.9 GB | 48k78k with q8 cache | 154tok/sest. | 3023 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 34.6 GB | 184k256k with q8 cache | 23tok/sest. | 477 tok/s | chat, coding, long documents |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 39.0 GB | 332k528k with q8 cache | 160tok/sest. | 1394 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.9 GB | 256k | 131tok/sest. | 3818 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.7 GB | 256k | 27tok/sest. | 535 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.7 GB | 256k | 99tok/sest. | 3397 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.9 GB | 49k79k with q8 cache | 187tok/sest. | 3596 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.9 GB | 256k | 131tok/sest. | 3818 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.2 GB | 198k | 71tok/sest. | 1994 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.2 GB | 144k262k with q8 cache | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.7 GB | 256k | 140tok/sest. | 4357 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.9 GB | 662k902k with q8 cache | 180tok/sest. | 3291 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.9 GB | 128k | 155tok/sest. | 2851 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.1 GB | 165k256k with q8 cache | 78tok/sest. | 1756 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.3 GB | 40k | 19tok/sest. | 332 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.5 GB | 256k | 62tok/sest. | 1240 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 256k | 78tok/sest. | 1546 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.2 GB | 128k | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 30.5 GB | 128k | 26tok/sest. | 568 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.3 GB | 55k102k with q8 cache | 19tok/sest. | 381 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.3 GB | 205k256k with q8 cache | 42tok/sest. | 859 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.5 GB | 40k | 40tok/sest. | 772 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.5 GB | 128k | 62tok/sest. | 1273 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.5 GB | 40k | 62tok/sest. | 1273 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.6 GB | 16k | 37tok/sest. | 776 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 256k | 149tok/sest. | 2892 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.5 GB | 256k | 61tok/sest. | 1230 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.6 GB | 128k | 57tok/sest. | 1171 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 128k | 91tok/sest. | 1942 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 125k | 187tok/sest. | 6351 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 128k | 77tok/sest. | 1345 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.8 GB | 32k | 892tok/sest. | 13832 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 676tok/sest. | 12993 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 449tok/sest. | 6194 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.5 GB | 128k | 294tok/sest. | 5204 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.7 GB | 128k | 204tok/sest. | 3108 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.9 GB | 1024k | 194tok/sest. | 3052 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.4 GB | 128k | 171tok/sest. | 3520 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.4 GB | 32k | 171tok/sest. | 3228 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.4 GB | 128k | 158tok/sest. | 4586 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.2 GB | 256k | 145tok/sest. | 2892 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.8 GB | 128k | 132tok/sest. | 2255 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 7.0 GB | 128k | 127tok/sest. | 2364 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 17.6 GB | 128k | 121tok/sest. | 3446 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.4 GB | 128k | 117tok/sest. | 3446 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.5 GB | 256k | 117tok/sest. | 2259 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.1 GB | 128k | 104tok/sest. | 3540 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.8 GB | 32k | 87tok/sest. | 1123 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.2 GB | 128k | 84tok/sest. | 1521 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.5 GB | 128k | 74tok/sest. | 1059 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.8 GB | 128k | 65tok/sest. | 1345 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.1 GB | 64k | 64tok/sest. | 1059 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.5 GB | 256k | 61tok/sest. | 1230 tok/s | chat, coding, agents, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 19.3 GB | 205k256k with q8 cache | 42tok/sest. | 859 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.5 GB | 128k | 38tok/sest. | 727 tok/s | chat, coding, long documents |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 22.3 GB | 256k | 36tok/sest. | 535 tok/s | chat, coding, agents, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.2 GB | 128k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.2 GB | 40k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.2 GB | 40k | 27tok/sest. | 573 tok/s | chat, coding, long documents |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.2 GB | 128k | 27tok/sest. | 564 tok/s | chat, coding, long documents |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.5 GB | 128k | 25tok/sest. | 515 tok/s | chat, coding, long documents |
| granite 4.2 30b IBM | Q8_0 | fits | 37.9 GB | 69k127k with q8 cache | 21tok/sest. | 438 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.2 GB | – | 37tok/sest. | 1197 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 60.5 GB | – | 28tok/sest. | 1759 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 48.8 GB | 24k44k with q8 cache | 29tok/sest. | 508 tok/s | chat, coding |
| Llama 3.3 70B Meta | Q4_K_M | offload | 50.5 GB | 22k41k with q8 cache | 8tok/sest. | 173 tok/s | chat |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 50.5 GB | 22k41k with q8 cache | 8tok/sest. | 173 tok/s | chat |
| GLM 4.5V Z.ai | Q4_K_M | offload | 65.9 GB | – | 7tok/sest. | 419 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 72.2 GB | – | 5tok/sest. | 400 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 70.8 GB | – | 2tok/sest. | 141 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 | – | – | – | – |
| 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 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 4.6 Z.ai | Q4_K_M | won't run | 213.2 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 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 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?
- Qwen 3.8 27B (Q8_0) fits fully in its memory at 32k context and generates at about 27 tok/s, an estimate from its memory bandwidth. 65 of the 125 models we track fit at that context.
- Can the NVIDIA RTX PRO 5000 Blackwell 48GB 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 5000 Blackwell 48GB and system RAM can hold.
- 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.