Instinct MI455X specs
AMD · Ramping · first available Oct 2026 (estimated). Dense compute, memory, bandwidth and power from the vendor's documents; each precision stays separate.
All accelerators · Compare with Instinct MI355X
Specifications
| Dense BF16 · FP32 accumulate | 5,033 TFLOPS |
|---|---|
| Dense FP8 · FP32 accumulate | 20,133 TFLOPS |
| Dense FP4 · FP32 accumulate | 40,265 TFLOPS |
| Memory | 432 GB · HBM |
| Memory bandwidth | 23.3 TB/s |
| Maximum chip power | 2,500 W |
| Interconnect | Helios rack-scale (72 GPU) |
| Process node | TSMC 2/3nm |
| First availability | Oct 2026est — estimated / secondary-source figure |
| Availability | Ramping |
MI400 Series flagship: CDNA 5 with HBM4. AMD's 20.1 PF FP8 and 40.3 PF MXFP4 are dense rates; it lists sparsity only for FP16/BF16/INT8. Customers: OpenAI 6 GW, Meta up to 6 GW (custom MI450-based GPU), Anthropic up to 2 GW. Launch month is an estimate.
Dense tensor rates with FP32 accumulation, never sparse or FP16-accumulate headline figures. Memory is in decimal GB. The est marker flags a value its vendor-document review did not confirm.
Rent it
No tracked rental quote. The site tracks providers' published list prices; this part may still be rentable under terms it does not record.
Value ratios
| $ per dense BF16 PFLOP-hour | No on-demand quote |
|---|---|
| Dense BF16 TFLOPS per watt | 2.01 |
| Bandwidth bytes per 1,000 BF16 FLOP | 4.63 |
| $ per dense FP8 PFLOP-hour | No on-demand quote |
| Dense FP8 TFLOPS per watt | 8.05 |
| Bandwidth bytes per 1,000 FP8 FLOP | 1.16 |
| $ per GB of memory per hour | No on-demand quote |
Prices divide the cheapest on-demand list price; theoretical ratios do not measure application speed.
Sources
Specifications reviewed . Row is the MI455X, whose dense rates AMD publishes directly (5.0 PF BF16, 20.1 PF FP8, 40.3 PF MXFP4); 23.3 TB/s HBM4 bandwidth and 2,500 W maximum board power.