NVIDIA Tesla P4

The Tesla P4 starts at $0.03 per GPU-hour, with a median of $0.03 across 1 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.

1 providers currently list the Tesla P4: Vast.ai. Compare their hourly pricing, regions and machine specs in the table above.

The Tesla P4 comes with 8 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.

With 8 GB of VRAM, a single Tesla P4 can serve models such as Granite 4.1 8B, Qwen3 8B, Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.

The largest models we track that fit across several Tesla P4 cards are Gemma 3 12B on 2 GPUs at 4-bit. A multi-GPU configuration means you rent and pay for every card for the whole run, and splitting a model across cards costs throughput as well: the GPUs exchange activations on every token, so performance depends on how fast they are wired together. We do not track interconnect, so check the provider's node specification. The table above gives the smallest configuration for each model at 16-bit, 8-bit and 4-bit precision.

The lowest on-demand price we currently track for the Tesla P4 is $0.03 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.