Quadro RTX 8000 Passive
NVIDIA
48GB VRAM · 624 GB/s bandwidth · 29.9 FP16 TFLOPS · 260W TDP
The Quadro RTX 8000 Passive has 48GB of VRAM with 624 GB/s memory bandwidth and 29.9 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (180 tok/s), Qwen 2.5 7B (95 tok/s), Llama 3.1 8B (90 tok/s). Models larger than ~82B parameters won't fit even at Q4. Electricity cost is approximately $28/month at 260W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 180 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 95 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 90 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | comfortable | 30 tok/s |
| Gemma 3 27B | 27.4B | 14 GB | tight | 26 tok/s |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | tight | 22 tok/s |
| Llama 3.3 70B | 70.6B | 35 GB | tight | 10 tok/s |
| Qwen 2.5 72B | 72.7B | 36 GB | tight | 9 tok/s |
| Llama 3.1 405B | 405B | 202 GB | won't fit | |
| DeepSeek R1 671B | 671B | 336 GB | won't fit |
Similar GPUs
| GPU | VRAM | BW | TFLOPS | TDP |
|---|---|---|---|---|
| Quadro RTX 8000 | 48GB | 672 GB/s | 32.6 | 260W |
| A40 PCIe | 48GB | 695 GB/s | 37.4 | 300W |
| M4 Max 48GB | 48GB | 546 GB/s | 36.9 | 75W |
| RTX A6000 | 48GB | 768 GB/s | 38.7 | 300W |
| M3 Max 48GB | 48GB | 400 GB/s | 32.8 | 75W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.