Hailo-10H
Hailo TechnologiesHailo's generative-AI edge accelerator, offered as an M.2 module and as a chip, delivering 40 TOPS at INT4 and 20 TOPS at INT8 with ~2.5W typical power. Unlike the Hailo-8, it adds a direct DDR interface so it can run LLMs and vision-language models (VLMs) on-device. It targets PCs, automotive, and edge devices needing local generative AI, supported by Hailo's software suite and a GenAI model zoo.
Verified live 2026-06-22 via primary sources. Proprietary silicon with published datasheets and an open GenAI model zoo, but the silicon and full toolchain are closed.
Openness
3 high confidence- schematics
- none
- toolchain
- partial (open runtime + MIT GenAI model zoo)
- datasheets
- public (June 2025)
- blobs
- required (proprietary silicon/firmware)
- retail
- open_market (M.2 modules purchasable)
Proprietary silicon with published datasheets and an open GenAI model zoo, but the silicon and full toolchain are closed.
- https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/ recorded 2026-06-22
official module product page for Hailo-10H
- https://github.com/hailo-ai/hailo_model_zoo_genai recorded 2026-06-22
MIT-licensed GenAI model zoo for Hailo-10H
Adoption
3 medium confidenceNewer generative-AI part; purchasable M.2 modules and a dedicated GenAI repo, but smaller install base than the Hailo-8.
- https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/ recorded 2026-06-22
productized, purchasable M.2 generative-AI module
Capability
4 high confidenceEdge-first part that runs generative models locally via a DDR interface, a step beyond CNN-only edge accelerators.
- https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/ recorded 2026-06-22
40 TOPS INT4 / 20 TOPS INT8, DDR interface, LLM/VLM support
Unchanged since 2026-08-01 (last edited, not re-checked)