AMD · CDNA 3
Instinct MI300X 192 GB rental prices and specifications
An AMD OAM accelerator with 192 GB of HBM3 and ROCm support, commonly deployed in eight-GPU systems for large-model inference and training.
Profile checked · Primary source ↗
- Memory
- 192 GB
- Bandwidth
- 5300 GB/s
- Current offers
- 0
- FP16 dense
- 1307.4 TFLOPS
- BF16 dense
- 1307.4 TFLOPS
- FP8 dense
- 2614.9 TFLOPS
- Interconnect
- Seven 128 GB/s Infinity Fabric links (896 GB/s aggregate) per MI300X OAM; PCIe Gen 5 x16 host links. Provider topology requires separate evidence.
Compare Instinct MI300X 192 GB cloud rentals
Use the exact 192 GB GPU profile when comparing rental quotes. Tables separate currencies, billing periods and rental terms; the required GPU count determines the whole-instance compute cost. Storage, transfer, taxes and other charges can be additional.
Source checks show when each price was actually observed. Historical quotes remain available separately and do not enter current price comparisons. Explore the sourced GPU rental price index or check a rental against your model requirements.
Manufacturer theoretical peak matrix throughput per OAM; dense values, not measured model throughput. · Specification source 1 ↗ · Specification source 2 ↗
Recently checked listings
Current rental offers
| GPU / provider | Instance price / offer | Terms / location |
|---|---|---|
| No offers match these filters. Try another billing period or currency. | ||
Previously observed offers
6 retained quotes with an old check, a different allocation, or unavailable status. These are excluded from current prices and capacity counts.
Show previously observed offers →Measured performance
Inference benchmarks
| Model | GPU setup | Engine | Quant. | Workload | Reported tok/s | Evidence | Max-load capacity scenarioUSD / million output tokens |
|---|---|---|---|---|---|---|---|
| No benchmark records have been supplied yet. | |||||||