Tesla P4
NVIDIA
8GB VRAM · 192 GB/s bandwidth · 0.1 FP16 TFLOPS · 75W TDP
The Tesla P4 has 8GB of VRAM with 192 GB/s memory bandwidth and 0.1 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (48 tok/s). Models larger than ~14B parameters won't fit even at Q4. Electricity cost is approximately $8/month at 75W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 48 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | tight | 25 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | tight | 23 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | won't fit | |
| Gemma 3 27B | 27.4B | 14 GB | won't fit | |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | won't fit | |
| Llama 3.3 70B | 70.6B | 35 GB | won't fit | |
| Qwen 2.5 72B | 72.7B | 36 GB | won't fit | |
| 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 |
|---|---|---|---|---|
| RTX A1000 | 8GB | 192 GB/s | 6.7 | 50W |
| Radeon Instinct MI6 | 8GB | 224 GB/s | 5.7 | 150W |
| Radeon Pro W5500 | 8GB | 224 GB/s | 10.4 | 125W |
| Radeon PRO W6600 | 8GB | 224 GB/s | 18.5 | 100W |
| GeForce RTX 3050 8 GB | 8GB | 224 GB/s | 9.1 | 130W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.