CA
Cambricon MLU370-X8
Official
MLUarch03 PCIe 2022 TSMC 7nm
FP32
24.0
TFLOPS
VRAM
48 GB
LPDDR5
TDP
250 W
96.0 TFLOPS/kW
Bandwidth
614 GB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Description | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|---|
| INT8 | 8-bit integer | 8 | 256.0 | 1.024 TFLOPS/W |
| FP16 | 16-bit floating point | 16 | 96.0 | 0.384 TFLOPS/W |
| BF16 | Brain Float 16 | 16 | 96.0 | 0.384 TFLOPS/W |
| FP32 | 32-bit floating point | 32 | 24.0 | 0.096 TFLOPS/W |
FP16 Efficiency
0.384 TFLOPS/W
96.0 TFLOPS / 250W
FP32 Efficiency
0.096 TFLOPS/W
24.0 TFLOPS / 250W
Power Specifications
TDP
250 W
Max Power
288 W
Power Connector
PCIe 8-pin
Cooling
Air
Memory Specifications
Capacity
48 GB
Type
LPDDR5
Bandwidth
614.4 GB/s
Interface
--
Hardware & Design
Form Factor
PCIe
Architecture
MLUarch03
Process Node
TSMC 7nm
Launch Year
2022
Variant
Standard
Market Segment
Professional
Full Specifications
| Memory | |
|---|---|
| VRAM | 48 GB |
| Memory Type | LPDDR5 |
| Bandwidth | 614 GB/s |
| Interconnect & I/O | |
| GPU-to-GPU | MLU-Link |
| Interconnect Bandwidth | 200 GB/s |
| Power & Thermal | |
| TDP | 250 W |
| General | |
| Form Factor | PCIe |
| Architecture | MLUarch03 |
| Launch Year | 2022 |
Documentation & Resources
Common Use Cases
General Compute AI/ML Workloads Data Processing
The Cambricon MLU370-X8 is optimized for high-performance computing tasks with MLUarch03 architecture delivering 24 TFLOPS of compute power.
Where to Rent
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersStay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.