作者： Jakub Rusinowski · 最后更新： 2026年7月21日
The flagship workstation GPU of the Blackwell generation: RTX 5090 silicon with 96 GB ECC GDDR7 at 1.79 TB/s. Fits Llama 3.3 70B at Q4 with room for long contexts and concurrent users, or GPT-oss 120B on a single card. The Workstation Edition (600W) needs a serious PSU; the Max-Q variant caps at 300W for quieter builds.
| VRAM | 96 GB |
| Memory Bandwidth | 1792 GB/s |
| TDP | 600 W |
| Architecture | Blackwell GB202 |
| Release Year | 2025 |
| MSRP at Launch | $8,565 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | 113–234 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | 21–44 tok/s (estimated) |
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
All models below run comfortably in 96 GB VRAM with Q4_K_M quantization.
| Llama 4 | Llama 4 Scout 17B · 67 GB VRAM · Q4_K_M · ollama run llama4:scout |
| Llama 3.3 | Llama 3.3 70B Instruct · 43 GB VRAM · Q4_K_M · ollama run llama3.3 |
| Llama 3.1 Family | Llama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| DeepSeek R1 | DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
| Qwen 3 | Qwen 3 32B · 21 GB VRAM · Q4_K_M · ollama run qwen3:32b |
| Qwen 3.5 | Qwen 3.5 122B-A10B · 74 GB VRAM · Q4_K_M · ollama run qwen3.5:122b |
| Qwen 3.6 | Qwen 3.6 35B-A3B · 22 GB VRAM · Q4_K_M · ollama run qwen3.6:35b-a3b |
| Qwen 3.7 | Qwen 3.7 35B-A3B · 22 GB VRAM · Q4_K_M · qwen3-7 |
Install Ollama then run the recommended model for this GPU:
ollama run llama3.3:70b
Yes — the NVIDIA RTX PRO 6000 Blackwell has 96 GB VRAM and runs The flagship workstation GPU of the Blackwell generation: RTX 5090 silicon with 96 GB ECC GDDR7 at 1.79 TB/s. Fits Llama
The NVIDIA RTX PRO 6000 Blackwell is estimated to run Llama 3.1 8B at 113–234 tok/s with Q4_K_M quantization. For Llama 3.3 70B the estimate is 21–44 tok/s. These are modelled estimates, not measurements — see /en/methodology.
With 96 GB you can run: Llama 4, Llama 3.3, Llama 3.1 Family, DeepSeek R1, Qwen 3. Use Ollama for the easiest setup: ollama run llama3.3:70b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?