SOPHON BM1684X Tensor Computing Processor

Edge tensor processor delivering 32 TOPS INT8 and 16 TFLOPS FP16 with an octa-core Cortex-A53 host and 32-channel HD video decode. Its TPU-MLIR toolchain runs LLaMA, Qwen and ChatGLM locally for on-robot language reasoning.

Price on request
Chip/SoCBM1684X
AI Compute (TOPS)32 TOPS INT8; 16 TFLOPS FP16/BF16
CPU8x Arm Cortex-A53 @2.3 GHz

Technical specifications

Product documentation
MANUFACTURER-REPORTED SPECIFICATIONS
Chip/SoCBM1684X
AI Compute (TOPS)32 TOPS INT8; 16 TFLOPS FP16/BF16
CPU8x Arm Cortex-A53 @2.3 GHz
MemoryLPDDR4X (12 GB on module SKUs)
OSLinux with SOPHON SDK / TPU-MLIR
InterfacesPCIe, GbE, USB 3.0, MIPI CSI
PowerApprox. 30 W (typical)

Reference specifications for the listed model. Options, test conditions and integration requirements should be confirmed for your selected configuration.

Supplier

SOPHGO Technologies Ltd. 北京算能科技有限公司
Beijing · est. 2019 · 500–1,000 employees

SOPHGO is a Chinese AI computing company founded in 2019 that designs the SOPHON tensor processing family and SG RISC-V CPUs. Its BM1684X delivers 32 TOPS INT8 with 32-channel video decode, powering edge AI boxes, robot perception servers and on-premise large-model inference.

View profile

Product documentation

Manufacturer and distributor references for model selection and technical review.

Configuration & quotation

Specify the exact model or variant, required interfaces and accessories, quantity and delivery destination. Use the quotation to confirm the supplied configuration, current availability and commercial terms.

Price range (USD)Price on request
MOQNegotiable
Lead time30-45 days

Ask for the current datasheet, delivery schedule, warranty scope and any documentation required for your destination.

Discuss this configuration

Related models

Considering SOPHON BM1684X Tensor Computing Processor? Share the quantity, configuration and destination so we can check fit, availability and quote requirements.

Request a quote

— The Sourcebotics sourcing desk

Chat