DEPLOYDatabase

Chip comparison

Cambricon MLU370-X8 vs NVIDIA B100 (Blackwell)

Side-by-side specs

Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.

FieldCambricon MLU370-X8NVIDIA B100 (Blackwell)
Process nodeTSMC N7TSMC 4NP
TDP250 W700 W
Memory48 GB LPDDR5192 GB HBM3e
Memory bandwidth8,000 GB/s
FP16 (dense)96 TFLOPS1,750 TFLOPS
BF16 (dense)1,750 TFLOPS
FP8 (dense)3,500 TFLOPS
INT8 (dense)256 TOPS
Form factorPCIeSXM6 (700 W envelope)
Announced2022-03-252024-03-18
Released2024-11-01

Robots running Cambricon MLU370-X8

No robots publicly running it yet.

Robots running NVIDIA B100 (Blackwell)

No robots publicly running it yet.

Data centers with Cambricon MLU370-X8

No data centers publicly running it yet.

Data centers with NVIDIA B100 (Blackwell)

No data centers publicly running it yet.

Common questions

Cambricon MLU370-X8 vs NVIDIA B100 (Blackwell): which is faster for training?

NVIDIA B100 (Blackwell) has 36.46x the dense FP16/BF16 throughput of the other (Cambricon MLU370-X8: 96 TFLOPS; NVIDIA B100 (Blackwell): 3,500 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Cambricon MLU370-X8 vs NVIDIA B100 (Blackwell): which has more memory?

NVIDIA B100 (Blackwell) carries more HBM (Cambricon MLU370-X8: 48 GB LPDDR5; NVIDIA B100 (Blackwell): 192 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Cambricon MLU370-X8 vs NVIDIA B100 (Blackwell): which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Cambricon MLU370-X8 0.38 (96 ÷ 250 W); NVIDIA B100 (Blackwell) 5.00 (3,500 ÷ 700 W). NVIDIA B100 (Blackwell) wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · Cambricon MLU370-X8 full page · NVIDIA B100 (Blackwell) full page.