NVIDIA RTX PRO 4000 Blackwell
24 GB · 672 GB/s · 145 W
In short
The NVIDIA RTX PRO 4000 Blackwell has 24 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 60 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at UD-Q6_K, at about 18 tok/s (estimated). We have no current price for the NVIDIA RTX PRO 4000 Blackwell in the UK.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the UK, 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 21.9 GB | 30k53k with q8 cache | 18tok/sest. | 369 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 22.4 GB | 23k40k with q8 cache | 18tok/sest. | 369 tok/s | chat |
| Gemma 4 31B | Q5_K_M | fits | 22.3 GB | 20k44k with q8 cache | 18tok/sest. | 322 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q4_K_M | fits | 21.7 GB | 74k116k with q8 cache | 120tok/sest. | 3164 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 22.3 GB | 24k42k with q8 cache | 18tok/sest. | 369 tok/s | chat |
| Gemma 4 26B-A4B | UD-Q6_K | fits | 22.7 GB | 36k62k with q8 cache | 63tok/sest. | 2411 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 21.5 GB | 84k131k with q8 cache | 121tok/sest. | 3164 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 21.1 GB | 48k82k with q8 cache | 63tok/sest. | 1771 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 20.0 GB | 28k52k with q8 cache | 20tok/sest. | 416 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | fits | 22.5 GB | 88k115k with q8 cache | 109tok/sest. | 3296 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 95tok/sest. | 2290 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 21.7 GB | 24k44k with q8 cache | 85tok/sest. | 2289 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 21.2 GB | 16k30k with q8 cache | 19tok/sest. | 285 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 32tok/sest. | 840 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 42tok/sest. | 1064 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 20.0 GB | 28k52k with q8 cache | 20tok/sest. | 416 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 21.2 GB | 16k30k with q8 cache | 19tok/sest. | 298 tok/s | chat |
| Gemma 3 27B | Q6_K | fits | 22.4 GB | 19k38k with q8 cache | 18tok/sest. | 374 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 57k104k with q8 cache | 27tok/sest. | 690 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 24tok/sest. | 642 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 99k128k with q8 cache | 42tok/sest. | 1123 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 42tok/sest. | 1123 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 24tok/sest. | 646 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 87tok/sest. | 2141 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 103k187k with q8 cache | 41tok/sest. | 1049 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 86k128k with q8 cache | 39tok/sest. | 1041 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 49tok/sest. | 1289 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 170tok/sest. | 7523 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 126k128k with q8 cache | 54tok/sest. | 1159 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 660tok/sest. | 15746 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 447tok/sest. | 10833 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 268tok/sest. | 4444 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 196tok/sest. | 4956 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 137tok/sest. | 3276 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 123tok/sest. | 3297 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 123tok/sest. | 2910 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 483k808k with q8 cache | 123tok/sest. | 2331 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q6_K | fits | 21.1 GB | 35k63k with q8 cache | 103tok/sest. | 3951 tok/s | chat, coding, agents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 97tok/sest. | 2182 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 179k256k with q8 cache | 92tok/sest. | 2235 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 91tok/sest. | 2346 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 89tok/sest. | 3625 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 256k | 84tok/sest. | 2141 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 16.8 GB | 128k | 74tok/sest. | 3056 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 71tok/sest. | 3056 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 49tok/sest. | 1251 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.7 GB | 32k | 49tok/sest. | 982 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 112k128k with q8 cache | 43tok/sest. | 1159 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 103k187k with q8 cache | 41tok/sest. | 1049 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 40tok/sest. | 907 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 34tok/sest. | 907 tok/s | chat, coding, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.4 GB | 57k104k with q8 cache | 27tok/sest. | 690 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 41k76k with q8 cache | 24tok/sest. | 629 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 17.6 GB | 43k79k with q8 cache | 23tok/sest. | 424 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 17.6 GB | 40k | 23tok/sest. | 424 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 17.6 GB | 43k79k with q8 cache | 23tok/sest. | 416 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 20.0 GB | 28k40k with q8 cache | 20tok/sest. | 424 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 20.6 GB | 48k84k with q8 cache | 20tok/sest. | 369 tok/s | chat |
| granite 4.2 30b IBM | Q5_K_M | fits | 22.3 GB | 12k22k with q8 cache | 18tok/sest. | 336 tok/s | chat |
| Muse Glimmer 30B meta-models | Q6_K | fits | 22.7 GB | 44k67k with q8 cache | 18tok/sest. | 342 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.0 GB | – | 18tok/sest. | 728 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 22tok/sest. | 1725 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.4 GB | – | 26tok/sest. | 972 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.4 GB | – | 8tok/sest. | 414 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 28tok/sest. | 2168 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 28.8 GB | – | 56tok/sest. | 2657 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 42.8 GB | – | 2tok/sest. | 101 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 42.8 GB | – | 2tok/sest. | 101 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 | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.5 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 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 4000 Blackwell
- Memory
- 24 GB GDDR7
- Memory bus
- 192-bit
- Memory bandwidth
- 672 GB/s
- FP16 compute
- 46.9 TFLOPS
- Software
- CUDA
- Board power
- 145 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA RTX PRO 4000 Blackwell have for AI models?
- The NVIDIA RTX PRO 4000 Blackwell has 24 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX PRO 4000 Blackwell can run locally?
- Qwen 3.8 27B (UD-Q6_K) fits fully in its memory at 8k context and generates at about 18 tok/s, an estimate from its memory bandwidth. 60 of the 125 models we track fit at that context.
- Can the NVIDIA RTX PRO 4000 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 4000 Blackwell and system RAM can hold.
- How much does the NVIDIA RTX PRO 4000 Blackwell cost in the UK?
- We have no current price for the NVIDIA RTX PRO 4000 Blackwell in the UK.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.