GUANGZHOU HUYU TECHNOLOGY CO., LTD.

Pour the model
into your palm

HUYU builds on-device LLM deployment for mobile. With our own inference engine, extreme quantization and mobile agent framework, large models run offline on ordinary phones — no network, no cloud, no data leaving the device.

≤ 4 bit
Mixed-precision quantization
8×
Model size reduction
0 bytes
Data uploaded to cloud
Android · iOS
Native on both platforms
01

Hu: the water scoop

Hu (戽) is an ancient tool for lifting water — scoop by scoop, farmers carried water uphill into the fields.

A frontier model in the cloud is like a great river: abundant, but behind a dam of latency, traffic cost, data residency and privacy rules. We build the scoop that carries that intelligence out of the river and into every device in hand.

The fish in our name is the device itself: small, fast, agile — swimming in its own waters. HUYU brings the water of models to the palm.

  • On-device firstWhat can run on the device does not go to the cloud. Inference, memory and knowledge stay local.
  • Engineering honestyReal-device power draw, heat and time-to-first-token are our only acceptance criteria.
  • Privacy by architectureWe do not delete data in the cloud. We keep it from leaving the device at all.
02

Six foundations of on-device inference

From operators and weights to memory and scheduling — closing the gap between large models and small phones, layer by layer.

◈

Inference engine

Custom graph executor with operator fusion and paged KV-cache reuse; unified scheduling across ARM CPU, GPU and NPU backends.

▤

Extreme quantization

2/3/4-bit mixed precision with group-wise quantization; weights packed offline, dequantized at runtime — balancing size, speed and accuracy.

◐

Memory and thermals

On-demand weight paging under a hard memory budget; temperature- and battery-aware dynamic scaling for long conversations.

◇

Multimodal on device

Text, vision and speech encoders run together on the device — photo Q&A, screenshot understanding and offline voice interaction.

⬡

On-device agent

Local tool calling, structured output and device-capability orchestration, with on-device retrieval for private knowledge bases.

⬢

One-tap delivery

Chunked model packages with resumable downloads, per-device rollout, hot updates and rollback — shipped inside your app.

03

Products

HUYU Edge SDK

Mobile inference

On-device inference SDK for Android and iOS: streaming generation, multi-turn chat, structured output and multimodal APIs — a few lines of code.

  • C/C++ core with Kotlin and Swift wrappers
  • GGUF and HUYU packed formats
  • Observable time-to-first-token and memory use

HUYU Studio

Model toolchain

A complete pipeline from raw weights to distributable model packages: quantization calibration, operator adaptation, size estimation and device compatibility testing.

  • One-click quantization with accuracy regression
  • Model sharding, signing and encryption
  • On-device benchmark reports

HUYU Agent Kit

On-device agents

An agent framework that runs inside the device: intent routing, tool calling, local knowledge base and memory — entirely offline.

  • On-device vector search and chunking
  • Tool orchestration with permission sandbox
  • Optional cloud fallback switch
04

Where it runs

Personal assistant

A system-level AI assistant that keeps working in airplane mode, weak coverage and underground garages.

Privacy-sensitive sectors

Clinical notes, legal and financial documents never leave the device — data minimization by design.

Smart hardware

Glasses, earbuds, car systems and robots gain language and vision understanding at low power.

Industry and fieldwork

Offline manual Q&A, equipment fault diagnosis and voice logging where there is no network.

05

About us

GUANGZHOU HUYU TECHNOLOGY CO., LTD. is based in Guangzhou, focused on on-device LLM deployment and mobile AI application development. We believe the default form of the next generation of intelligent applications is not in the cloud, but in the user's pocket.

Our work centres on three lines — inference engines, model compression and on-device agents — giving handset makers, enterprises and developers everything from model adaptation to shipped applications.

Company广州戽鱼科技有限公司
English nameGUANGZHOU HUYU TECHNOLOGY CO., LTD.
BusinessOn-device LLM deployment / mobile AI applications
BrandHUYU
LocationGuangzhou, China
Websitelocalai.mobi

Pour the model into your device

Technology partnerships, SDK trials and custom deployment — write to us.

xielaobanxxx@gmail.com