Hailo-10H

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)

form_factor

module (M.2 accelerator module, also sold as bare silicon)

Hailo publishes a public datasheet and open-sources its GenAI model zoo and HailoRT runtime under MIT and LGPL-2.1. But the Dataflow Compiler that turns a model into something the chip can run is closed and available only to customers, and no schematic or board file is published for the module.

• https://api.github.com/repos/hailo-ai/hailo_model_zoo_genai recorded 2026-08-14

  "Model zoo for Gen AI models for Hailo products" with license spdx_id MIT, 100 stars

• https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/ recorded 2026-06-22

  official module product page for Hailo-10H. Not re-fetchable - hailo.ai answers HTTP 403 to every automated request under every header set tried - so it keeps its recorded read

• https://raw.githubusercontent.com/hailo-ai/hailort/master/README.md recorded 2026-08-14

  "The master branch supports only the Hailo-10 and Hailo-15 device families"; MIT for libhailort/pyhailort/hailortcli and LGPL 2.1 for hailonet; developer-zone documentation "registration is required"; the PCIe driver ships device firmware

• https://up-board.org/hailo-10h-m2-ai-acceleration-module/ recorded 2026-08-14

  AAEON/UP's published spec table for the module - chipset, AI performance, interface, memory and speed, power, supported OS, host architectures, frameworks and model types. What it does NOT publish is any board file - "Package Contents - 1 x Quick Start Guide" is the whole of what ships, and no schematic, gerber or BOM is offered anywhere on the page, which is the evidence for schematics:none.

• https://www.geniatech.com/product/aim-m-h10/ recorded 2026-08-14

  a second vendor's purchasable Hailo-10 M.2 module - "Up to 40 TOPS AI performance", "M.2 Key-M form factor"

Hailo-10H is a newer generative-AI part, sold through at least two independent module vendors (AAEON/UP and Geniatech), with a dedicated GenAI model-zoo repository backing it. It has a smaller install base than the Hailo-8, whose runtime repository sees much more activity.

• https://api.github.com/repos/hailo-ai/hailo_model_zoo_genai recorded 2026-08-14

  the dedicated GenAI repo at 100 stars, 20 forks, last pushed 2026-04-15 - real but well behind HailoRT's 215 stars and 2026-08-11 push

• https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/ recorded 2026-10-08

  Product page with a How to Buy section: "You can buy small quantities online from one of our global distributors or find a distributor near you for bulk orders."

• https://up-board.org/hailo-10h-m2-ai-acceleration-module/ recorded 2026-10-08

  AAEON/UP shipping the Hailo-10H M.2 module as a listed product with full specifications

• https://www.geniatech.com/product/aim-m-h10/ recorded 2026-10-08

  "Hailo-10 M.2 AI Accelerator Card" - a second independent vendor productizing the part

The DDR interface lets the Hailo-10H run LLMs, VLMs and Stable Diffusion locally, as both AAEON/UP and Geniatech describe. That puts it a step above the Hailo-8, which is limited to vision models and bounded by on-die memory.

• 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. Not re-fetchable - hailo.ai answers HTTP 403 to every automated request - so it keeps its recorded read

• https://up-board.org/hailo-10h-m2-ai-acceleration-module/ recorded 2026-09-29

  AAEON/UP spec table gives "40 TOPS @ INT4 | 20 TOPS @ INT8" and "Hailo-10H includes a direct DDR interface, allowing it to scale for large models such as LLMs, VLMs, Stable Diffusion" and "Consumes 2.5W (typical)".

• https://www.geniatech.com/product/aim-m-h10/ recorded 2026-09-29

  Geniatech page: "Up to 40 TOPS AI performance"; "Runs LLMs, VLMs, and Stable Diffusion locally"; "M.2 Key-M form factor"; "Hailo-10 M.2 AI Accelerator Card".