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 8k context it runs 61 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 19 tok/s (estimated). We have no current price for the NVIDIA RTX PRO 4500 Blackwell 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 51k89k with q8 cache | 19tok/sest. | 432 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 57k100k with q8 cache | 19tok/sest. | 432 tok/s | chat |
| Gemma 4 31B | Q6_K | fits | 25.6 GB | 76k143k with q8 cache | 21tok/sest. | 377 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q6_K | fits | 29.8 GB | 71k112k with q8 cache | 119tok/sest. | 3706 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 57k100k with q8 cache | 19tok/sest. | 432 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.1 GB | 216k256k with q8 cache | 73tok/sest. | 2824 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 27.8 GB | 148k232k with q8 cache | 126tok/sest. | 3706 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.8 GB | 18k31k with q8 cache | 58tok/sest. | 2074 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 45k82k with q8 cache | 21tok/sest. | 488 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 29.0 GB | 214k256k with q8 cache | 112tok/sest. | 3861 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 28.8 GB | 196k267k with q8 cache | 172tok/sest. | 3522 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 127tok/sest. | 2682 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 24.9 GB | 73k131k with q8 cache | 102tok/sest. | 2681 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 27.8 GB | 22k40k with q8 cache | 19tok/sest. | 334 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 42tok/sest. | 984 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 56tok/sest. | 1246 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 45k82k with q8 cache | 21tok/sest. | 488 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 27.8 GB | 22k40k with q8 cache | 19tok/sest. | 349 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 28.5 GB | 42k79k with q8 cache | 19tok/sest. | 438 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 106k194k with q8 cache | 35tok/sest. | 809 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 33tok/sest. | 752 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 128k | 56tok/sest. | 1315 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 56tok/sest. | 1315 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 32tok/sest. | 757 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 116tok/sest. | 2508 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 160k256k with q8 cache | 55tok/sest. | 1229 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 128k | 52tok/sest. | 1220 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 66tok/sest. | 1510 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 227tok/sest. | 8813 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 128k | 72tok/sest. | 1358 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 879tok/sest. | 18445 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 596tok/sest. | 12690 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 357tok/sest. | 5205 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 261tok/sest. | 5805 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 183tok/sest. | 3837 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 164tok/sest. | 3862 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 164tok/sest. | 3408 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 678k1024k with q8 cache | 163tok/sest. | 2730 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 130tok/sest. | 2556 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 254k256k with q8 cache | 123tok/sest. | 2618 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 122tok/sest. | 2748 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.1 GB | 82k128k with q8 cache | 119tok/sest. | 4628 tok/s | chat, coding, agents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 118tok/sest. | 4246 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 256k | 112tok/sest. | 2508 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 16.8 GB | 128k | 99tok/sest. | 3580 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 95tok/sest. | 3580 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 65tok/sest. | 1465 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.7 GB | 32k | 65tok/sest. | 1151 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 128k | 58tok/sest. | 1358 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 160k256k with q8 cache | 55tok/sest. | 1229 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 54tok/sest. | 1062 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 46tok/sest. | 1062 tok/s | chat, coding, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.4 GB | 106k194k with q8 cache | 35tok/sest. | 809 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 83k128k with q8 cache | 32tok/sest. | 737 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 20.6 GB | 165k256k with q8 cache | 26tok/sest. | 432 tok/s | chat, coding, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 45k82k with q8 cache | 21tok/sest. | 496 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 21tok/sest. | 496 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 21tok/sest. | 496 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.3 GB | 45k82k with q8 cache | 21tok/sest. | 488 tok/s | chat |
| granite 4.2 30b IBM | Q6_K | fits | 25.6 GB | 30k56k with q8 cache | 21tok/sest. | 393 tok/s | chat |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.0 GB | 27k42k with q8 cache | 17tok/sest. | 401 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.0 GB | – | 30tok/sest. | 993 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 31tok/sest. | 2325 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 51.9 GB | – | 13tok/sest. | 766 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.4 GB | – | 48tok/sest. | 1329 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.4 GB | – | 12tok/sest. | 560 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 40tok/sest. | 2924 tok/s | chat, coding, agents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 42.8 GB | – | 4tok/sest. | 136 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 42.8 GB | – | 4tok/sest. | 136 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 | – | – | – | – |
| 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 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 (Q8_0) fits fully in its memory at 8k context and generates at about 19 tok/s, an estimate from its memory bandwidth. 61 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 92 GB at 8k 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 US?
- We have no current price for the NVIDIA RTX PRO 4500 Blackwell in the US.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.