NVIDIA RTX PRO 4500 Blackwell
32 GB · 896 GB/s · 200 W
In short
The NVIDIA RTX PRO 4500 Blackwell has 32 GB of GDDR7 memory with 896 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 58 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q6_K, at about 20 tok/s (estimated). We have no current price for the NVIDIA RTX PRO 4500 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q6_K | fits | 27.4 GB | 121k213k with q8 cache | 20tok/sest. | 361 tok/s | chat, coding, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.2 GB | 140k245k with q8 cache | 21tok/sest. | 361 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q6_K | fits | 30.3 GB | 76k143k with q8 cache | 18tok/sest. | 330 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q6_K | fits | 31.2 GB | 71k112k with q8 cache | 84tok/sest. | 2175 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.1 GB | 141k246k with q8 cache | 21tok/sest. | 361 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.5 GB | 216k256k with q8 cache | 58tok/sest. | 2227 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.3 GB | 148k232k with q8 cache | 87tok/sest. | 2175 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 27.4 GB | 133k198k with q8 cache | 44tok/sest. | 1079 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.1 GB | 78k142k with q8 cache | 19tok/sest. | 356 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 29.6 GB | 214k256k with q8 cache | 100tok/sest. | 2681 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.6 GB | 196k267k with q8 cache | 139tok/sest. | 1747 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 128k | 83tok/sest. | 1664 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 30.4 GB | 73k131k with q8 cache | 37tok/sest. | 778 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 256k | 40tok/sest. | 856 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 256k | 47tok/sest. | 1048 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 27.1 GB | 114k128k with q8 cache | 20tok/sest. | 405 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.1 GB | 78k128k with q8 cache | 19tok/sest. | 356 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.4 GB | 106k194k with q8 cache | 22tok/sest. | 501 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.7 GB | 40k | 21tok/sest. | 439 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.2 GB | 128k | 30tok/sest. | 692 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.2 GB | 40k | 30tok/sest. | 692 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.1 GB | 16k | 19tok/sest. | 440 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 83tok/sest. | 1816 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.0 GB | 160k256k with q8 cache | 31tok/sest. | 685 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.8 GB | 128k | 28tok/sest. | 633 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 55tok/sest. | 1372 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 125k | 78tok/sest. | 2928 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 128k | 37tok/sest. | 744 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 416tok/sest. | 6495 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 340tok/sest. | 7364 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 246tok/sest. | 4014 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 147tok/sest. | 2690 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 128k | 101tok/sest. | 1516 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.2 GB | 678k1024k with q8 cache | 101tok/sest. | 1861 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.0 GB | 128k | 92tok/sest. | 2714 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.4 GB | 256k | 82tok/sest. | 1816 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.5 GB | 128k | 81tok/sest. | 1839 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.5 GB | 32k | 81tok/sest. | 1729 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 18.8 GB | 128k | 65tok/sest. | 1866 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.6 GB | 128k | 63tok/sest. | 1866 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.4 GB | 128k | 62tok/sest. | 1154 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 9.7 GB | 128k | 60tok/sest. | 1192 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.0 GB | 254k256k with q8 cache | 52tok/sest. | 1142 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.3 GB | 32k | 51tok/sest. | 614 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.1 GB | 128k | 47tok/sest. | 871 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 29.8 GB | 82k128k with q8 cache | 45tok/sest. | 1678 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.9 GB | 128k | 44tok/sest. | 588 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.5 GB | 64k | 38tok/sest. | 588 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.0 GB | 128k | 32tok/sest. | 744 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.0 GB | 160k256k with q8 cache | 31tok/sest. | 685 tok/s | chat, coding, agents, long documents |
| Muse Glimmer 30B meta-models | Q6_K | fits | 23.8 GB | 128k | 23tok/sest. | 364 tok/s | chat, coding, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 24.4 GB | 106k194k with q8 cache | 22tok/sest. | 501 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 24.5 GB | 165k256k with q8 cache | 22tok/sest. | 361 tok/s | chat, coding, long documents |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 26.7 GB | 93k128k with q8 cache | 20tok/sest. | 360 tok/s | chat, coding |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 26.7 GB | 40k | 20tok/sest. | 360 tok/s | chat, coding |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 26.7 GB | 93k128k with q8 cache | 20tok/sest. | 356 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 27.7 GB | 83k128k with q8 cache | 19tok/sest. | 400 tok/s | chat, coding |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 29.1 GB | 40k | 19tok/sest. | 360 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.7 GB | – | 19tok/sest. | 638 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.8 GB | – | 19tok/sest. | 1375 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.6 GB | – | 11tok/sest. | 658 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.9 GB | – | 28tok/sest. | 642 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 54.8 GB | – | 4tok/sest. | 181 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.8 GB | – | 22tok/sest. | 1568 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.5 GB | 40k | 7tok/sest. | 171 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.6 GB | 47k88k with q8 cache | 7tok/sest. | 211 tok/s | chat |
| granite 4.2 30b IBM | Q4_K_M | offload | 33.9 GB | 54k100k with q8 cache | 9tok/sest. | 254 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 71.8 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 224.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 388.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX PRO 4500 Blackwell
- Memory
- 32 GB GDDR7
- Memory bus
- 256-bit
- Memory bandwidth
- 896 GB/s
- FP16 compute
- 54.94 TFLOPS
- Software
- CUDA
- Board power
- 200 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA RTX PRO 4500 Blackwell have for AI models?
- The NVIDIA RTX PRO 4500 Blackwell has 32 GB of GDDR7 memory with 896 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX PRO 4500 Blackwell can run locally?
- Qwen 3.8 27B (Q6_K) fits fully in its memory at 64k context and generates at about 20 tok/s, an estimate from its memory bandwidth. 58 of the 125 models we track fit at that context.
- Can the NVIDIA RTX PRO 4500 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 4500 Blackwell and system RAM can hold.
- How much does the NVIDIA RTX PRO 4500 Blackwell cost in the UK?
- We have no current price for the NVIDIA RTX PRO 4500 Blackwell in the UK.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.