AMD Instinct MI350X OAM
Performance
Peak theoretical throughput by precision type
| Precision | Dense | 2:4 Sparse |
|---|---|---|
FP64 64-bit floating point | 72TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
FP32 32-bit floating point | 144TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
TF32 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
BF16 Brain Float 16 | 2,310TFLOPS | 4,619TFLOPS |
FP16 16-bit floating point | 2,310TFLOPS | 4,619TFLOPS |
FP8 8-bit floating point | 4,614TFLOPS | 9,227TFLOPS |
FP6 | 9,228TFLOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP4 4-bit floating point | 9,228TFLOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
INT8 8-bit integer | 4,614TOPS | 9,227TOPS |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 1000 W.
The Instinct MI350X OAM in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
CDNA 4
Form Factor
OAM
Launch Year
2025
Process Node
3nm/6nm
Memory
288 GB
Bandwidth
8,000 GB/s
TDP
1.0 kW
Max power (Flopper estimate)
~1.1 kW est. Flopper estimate: 1000 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| Memory | 288 GB |
| Memory Type | No verified data available |
| Bandwidth | 8.0 TB/s |
| Interface Width | No verified data available |
| Power & Thermal | |
| TDP | 1.0 kW |
| Max power (Flopper estimate) | ~1.1 kW est. |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | OAM |
| Architecture | CDNA 4 |
| Process Node | 3nm/6nm |
| Launch Year | 2025 |
Datasheet & Resources
Flopper Datasheet
AMD Instinct MI350X OAM specifications, generated from our database. Printable.
Vendor product page
AMD documentation for the Instinct MI350X OAM
AMD Instinct Documentation
ROCm guides, architecture details
Data Provenance
Every figure traced to a source
Primary Source
- Document
- —
- Publisher
- AMD
- Published
- No verified data available
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 8 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$6.16 / GPU-hr
Lowest of 2 live listings across 1 provider
Price history and every provider on the pricing page. Some links are affiliate links.
Similar GPUs
Frequently Asked Questions
How many TFLOPS does the AMD Instinct MI350X have?
The AMD Instinct MI350X delivers 144 TFLOPS FP32, 2,310 TFLOPS FP16 and 4,614 TFLOPS FP8 at peak.
What is the power consumption of the AMD Instinct MI350X?
The AMD Instinct MI350X has a TDP (Thermal Design Power) rating of 1,000 watts.
How much memory does the AMD Instinct MI350X have?
The AMD Instinct MI350X is equipped with 288 GB of memory with 8,000 GB/s of memory bandwidth.
What architecture is the AMD Instinct MI350X based on?
The AMD Instinct MI350X is based on the CDNA 4 architecture, launched in 2025.
How much does the AMD Instinct MI350X cost to rent?
The AMD Instinct MI350X rents from $6.16 per GPU-hour across 1 cloud provider, the lowest of 2 live listings Flopper tracks. The pricing page lists every provider and the price history.
When did the AMD Instinct MI350X come out?
The AMD Instinct MI350X launched in 2025 on the CDNA 4 architecture.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.