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 68 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 14 tok/s (estimated). The best new price for the NVIDIA RTX PRO 4000 Blackwell in Canada is $2,810 at Amazon.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonNvidia RTX 4000 Ada Retail | New | $2,810 | In stock | 1 h ago | Buy |
| AmazonNvidia RTX Pro 4000 Blackwell 24GB Gddr7 | New | $4,233 | In stock | 2 h ago | Buy |
| AmazonNVIDIA RTX PRO 4000 SFF Blackwell 24GB GDDR7 ECC | New | $4,668 | In stock | 2 h ago | Buy |
| AmazonNVIDIA RTX PRO 4000 Blackwell Graphics Card | New | $4,671 | In stock | 2 h ago | Buy |
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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 256k | 14tok/sest. | 369 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.4 GB | 224k256k with q8 cache | 68tok/sest. | 977 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 14tok/sest. | 369 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 14k23k with q8 cache | 95tok/sest. | 2467 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.9 GB | 172k256k with q8 cache | 12tok/sest. | 322 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.8 GB | 296k471k with q8 cache | 97tok/sest. | 1276 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 76tok/sest. | 3164 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 14tok/sest. | 369 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 256k | 55tok/sest. | 2411 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.8 GB | 18k34k with q8 cache | 34tok/sest. | 582 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 15k24k with q8 cache | 121tok/sest. | 3101 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 76tok/sest. | 3164 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 31.2 GB | 198k | 44tok/sest. | 1771 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 137k251k with q8 cache | 16tok/sest. | 416 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.8 GB | 256k | 73tok/sest. | 3296 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.9 GB | 588k802k with q8 cache | 97tok/sest. | 3007 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 95tok/sest. | 2290 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 32.1 GB | 155k256k with q8 cache | 63tok/sest. | 2289 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.6 GB | 40k | 11tok/sest. | 285 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 32tok/sest. | 840 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 42tok/sest. | 1064 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 16tok/sest. | 416 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 128k | 14tok/sest. | 374 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.6 GB | 51k95k with q8 cache | 11tok/sest. | 298 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 9tok/sest. | 139 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 199k256k with q8 cache | 27tok/sest. | 690 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 24tok/sest. | 642 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 42tok/sest. | 1123 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 42tok/sest. | 1123 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 24tok/sest. | 646 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 87tok/sest. | 2141 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 41tok/sest. | 1049 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 39tok/sest. | 1041 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 49tok/sest. | 1289 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 170tok/sest. | 7523 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 54tok/sest. | 1159 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 660tok/sest. | 15746 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 447tok/sest. | 10833 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 268tok/sest. | 4444 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.1 GB | 128k | 196tok/sest. | 4956 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.0 GB | 128k | 137tok/sest. | 3276 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.3 GB | 128k | 123tok/sest. | 3297 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.3 GB | 32k | 123tok/sest. | 2910 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.3 GB | 1024k | 123tok/sest. | 2331 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 5.1 GB | 128k | 97tok/sest. | 2182 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.4 GB | 256k | 92tok/sest. | 2235 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.4 GB | 128k | 91tok/sest. | 2346 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.5 GB | 128k | 89tok/sest. | 3951 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 128k | 89tok/sest. | 3625 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.7 GB | 256k | 84tok/sest. | 2141 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 17.2 GB | 128k | 74tok/sest. | 3056 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.0 GB | 128k | 71tok/sest. | 3056 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 9.1 GB | 128k | 49tok/sest. | 1251 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.1 GB | 32k | 49tok/sest. | 982 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 43tok/sest. | 1159 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 41tok/sest. | 1049 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.8 GB | 128k | 40tok/sest. | 907 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.4 GB | 64k | 34tok/sest. | 907 tok/s | chat, coding, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.8 GB | 199k256k with q8 cache | 27tok/sest. | 690 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 17.3 GB | 128k | 24tok/sest. | 629 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 21.0 GB | 256k | 20tok/sest. | 369 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 16tok/sest. | 424 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 16tok/sest. | 424 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.7 GB | 40k | 16tok/sest. | 424 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 16tok/sest. | 416 tok/s | chat |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.4 GB | 128k | 13tok/sest. | 342 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 32.1 GB | 65k120k with q8 cache | 13tok/sest. | 336 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 9tok/sest. | 139 tok/s | – |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 59.9 GB | – | 29tok/sest. | 1434 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 26tok/sest. | 805 tok/s | chat, coding, long documents |
| GLM 4.5V Z.ai | Q4_K_M | offload | 61.8 GB | – | 9tok/sest. | 475 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 68.2 GB | – | 7tok/sest. | 451 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 63.6 GB | – | 2tok/sest. | 113 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 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 | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 156.2 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 73.7 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 384.2 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.8 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.7 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 748.2 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.4 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.8 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.7 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 (Q8_0) fits fully in its memory at 8k context and generates at about 14 tok/s, an estimate from its memory bandwidth. 68 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 Canada?
- The best new price for the NVIDIA RTX PRO 4000 Blackwell in Canada is $2,810 at Amazon.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.