Infrastructure / Edge AI hardware

Hailo-8

An edge AI inference accelerator delivering up to 26 TOPS at roughly 2.5W typical power, built by Hailo Technologies (Israel). It is sold as a bare chip and in M.2, mPCIe, and PCIe card form factors with on-die memory, supporting TensorFlow, TFLite, Keras, PyTorch, and ONNX via the Hailo Dataflow Compiler and HailoRT runtime. It is widely deployed in robotics, ADAS, security cameras, and industrial vision.

Verified live 2026-06-22 via primary sources. Proprietary silicon with an open source runtime and public product briefs, but the model-compiler toolchain requires registration and silicon is closed.

Openness

3 high confidence

3.0

schematics: none
toolchain: partial (open runtime (HailoRT) + closed/registration Dataflow Compiler)
datasheets: brief (public briefs)
blobs: required (proprietary silicon + firmware)
retail: open_market (global modules)

Proprietary silicon with an open source runtime and public product briefs, but the model-compiler toolchain requires registration and silicon is closed.

https://hailo.ai/products/ai-accelerators/hailo-8-ai-accelerator/ recorded 2026-06-22
official product page: form factors, frameworks, software suite
https://github.com/hailo-ai/hailort recorded 2026-06-22
open source HailoRT inference runtime

Adoption

4 high confidence

4.0

Retail-available modules and a large developer base; vendor reports 100K+ users and hundreds of deployed customer products, with an active GitHub org.

https://hailo.ai/products/ai-accelerators/hailo-8-ai-accelerator/ recorded 2026-06-22
vendor claim of >100K users and hundreds of customer products

Capability

3 high confidence

3.0

Strong dedicated CNN inference throughput for the edge, but vision-oriented and limited to models that fit on-die memory.

https://hailo.ai/products/ai-accelerators/hailo-8-ai-accelerator/ recorded 2026-06-22
26 TOPS, 2.5W typical, on-die memory

Unchanged since 2026-08-01 (last edited, not re-checked)