Hardware · NVIDIA
What AI models can the NVIDIA RTX PRO 4000 Blackwell run?
- VRAM
- 24.0 GB
- Usable for models
- 24.0 GB
- Memory bandwidth
- 672 GB/s
- FP16 compute
- 40.0 TFLOPS
- Released
- 2025
Specifications
| Maker | NVIDIA |
|---|---|
| Type | Workstation / datacenter graphics card |
| Video memory (VRAM) | 24.0 GB |
| Usable for AI models | 24.0 GB |
| Memory bandwidth | 672 GB/s |
| FP16 compute | 40.0 TFLOPS |
| Interface | PCIe 5.0 |
| Released | 2025 |
1 product with the NVIDIA RTX PRO 4000 Blackwell
Best LLMs for the NVIDIA RTX PRO 4000 Blackwell
| Grade · points | Model | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Gemma 4 26B-A4B | Q6_K | 23.4 GB | 75.3 tok/s | Tight fit |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 40.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.6 35B-A3B | Q4_K_M | 23.9 GB | 137 tok/s | Tight fit |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 12.9/15, Memory use 15.0/15 | Qwen3.8 27B | Q4_K_M | 19.3 GB | 29.7 tok/s | Runs well |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.5 35B-A3B | Q4_K_M | 23.9 GB | 137 tok/s | Tight fit |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 12.9/15, Memory use 15.0/15 | Qwen3.6 27B | Q4_K_M | 19.3 GB | 29.7 tok/s | Runs well |
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 12.9/15, Memory use 15.0/15 | Qwen3.5 27B | Q4_K_M | 19.3 GB | 29.7 tok/s | Runs well |
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.5 35B-A3B | Q4_K_M | 23.9 GB | 137 tok/s | Tight fit |
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Apodex 1.1 Mini (35B-A3B) | Q4_K_M | 23.9 GB | 137 tok/s | Tight fit |
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.0 35B-A3B | Q4_K_M | 23.9 GB | 137 tok/s | Tight fit |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | GLM-4.7 Flash (30B-A3B) | Q4_K_M | 21.3 GB | 137 tok/s | Tight fit |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 15.0/15 | TMax 27B | Q4_K_M | 19.0 GB | 30.2 tok/s | Runs well |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Agents-A1 35B-A3B | Q4_K_M | 23.4 GB | 137 tok/s | Tight fit |
Best Image models for the NVIDIA RTX PRO 4000 Blackwell
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | FLUX.2 [klein] 9B | FP8 | 19.9 GB | 2.8 s | Runs well |
| 90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 1.7 s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15 | Z-Image Turbo | Q8 GGUF | 13.0 GB | 5.0 s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 15.0/15 | FLUX.1 Krea [dev] | FP8 | 19.6 GB | 19 s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 15.0/15 | FLUX.1 [dev] | FP8 | 19.6 GB | 19 s | Runs well |
| 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | FLUX.1 [schnell] | FP8 | 19.6 GB | 3.1 s | Runs well |
Best Video models for the NVIDIA RTX PRO 4000 Blackwell
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | LTX-Video 2B | FP16 | 17.5 GB | 43 s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 14.3/15 | CogVideoX 5B I2V | FP8 | 14.9 GB | 4.7 min | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 7.9/15, Memory use 15.0/15 | FramePack I2V (HunyuanVideo 13B) | FP8 | 19.6 GB | 10.9 min | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | CogVideoX 2B | FP16 | 17.5 GB | 1.7 min | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 13.8/15 | CogVideoX 5B | FP8 | 14.3 GB | 4.7 min | Runs well |
Best LLMs by task on this hardware Open in Model Finder
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.