AMD Instinct MI300X

The Instinct MI300X starts at $1.71 per GPU-hour, with a median of $2.80 across 6 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.

3 providers currently list the Instinct MI300X: Cyfuture AI, TensorWave, Runpod. Compare their hourly pricing, regions and machine specs in the table above.

The Instinct MI300X comes with 192 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.

With 192 GB of VRAM, a single Instinct MI300X can serve models such as DeepSeek V4 Flash, Qwen3 235B-A22B, Laguna-S 2.1, gpt-oss-120b. 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 Instinct MI300X cards are DeepSeek V4 Pro on 8 GPUs at 4-bit, Kimi K2.5 on 4 GPUs at 4-bit, GLM-5.2 on 4 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 Instinct MI300X is $1.71 per GPU-hour at TensorWave. Because providers update pricing and availability frequently, check the live table above before you launch.