Compare GPUs
Compare 2-4 public GPU options using the same database-backed price, inventory and specification records.
| GPU |
NVIDIA L4 24GB |
|---|---|
| Monthly rental | USD 250/month |
| Hourly equivalent | ~ USD 0.34/hour |
| VRAM | 24 GB GDDR6 |
| Architecture | Ada Lovelace |
| Bandwidth | 300 GB/s |
| Form factor | PCIe low-profile accelerator card |
| Interface | PCIe Gen4 x16 |
| TDP | 72 W |
| FP32 | 30.3 TFLOPS dense |
| TF32 | 60 TFLOPS dense / 120 TFLOPS sparse |
| BF16 | 121 TFLOPS dense / 242 TFLOPS sparse |
| FP16 | 121 TFLOPS dense / 242 TFLOPS sparse |
| FP8 | 242.5 TFLOPS dense / 485 TFLOPS sparse |
| INT8 | 242.5 TOPS dense / 485 TOPS sparse |
| MIG | Not supported |
| NVLink | Not supported |
| Availability | Available |
| Frameworks | PyTorch, TensorFlow, JAX, Hugging Face, vLLM, TensorRT, ONNX Runtime, CUDA |
| Model compatibility guidance | Usually requires multiple GPUs or stronger quantisation |
| Action | Configure & rent |