New

Open-source AI local build service

Reference:

Condition: New product

Add date: 03/09/2026

Last modification date: 03/18/2026

Brand: CA

Warning: Last items in stock!

By buying this product you can collect up to 42 loyalty points. Your cart will total 42 points that can be converted into a voucher of $ 210.00.

$ 37,890.00

Quantity

Editions

Teams of 1-5 people, 2h/day/user @~30token/s
Teams of 6-12 people, 2h/day/user @~30token/s

門市到付 / 過數易 / 貨到付款

More info

Open-Source AI Local Build Service

Designed for enterprises with confidentiality requirements · Runs entirely on your internal GPU servers · Data never passes through third parties

Zero Data Leakage

All computation and temporary storage are within the company's internal GPU servers, never handled by third parties, complying with strict confidentiality regulations.

Dedicated Local AI Server

The platform can connect to multiple local GPU servers, with linearly scalable computing power.

Internal Exclusive Platform

Preloaded with Open WebUI / LM Studio style portal, customizable dedicated domain.

Up to 120B Class Models

Supports open-source models up to 120B (120 billion) parameters

Up to 200K Context Length

Can process approximately 200,000 Chinese characters of ultra-long documents, code, reports, meeting deep analysis and long conversation scenarios.

Freely Switch/Connect Multiple Models

One-click switch between open-source LLM/VLM in the management interface, connect multiple model backends simultaneously for output comparison.

* Recommended sweet spot (approx. 80B, 128k context length)
* 80B model averages about 35 tokens/sec, suitable for groups under 10 people.

Dedicated AI Hardware + Software Bundle

1-5 Person Team

Package 1

$9,000 Hardware + $28,890 Platform/Service

Total $37,890 / first year

Dedicated AI platform with 2nd-level domain
1× Blackwell G10 128GB unified memory
Supports open-source LLM / VLM 80B and below
Computing power reaches 2 hours/person/day @~30token/s
1-year local hosting (4 vCPU · 16GB RAM · 100GB · No GPU)

Top-level domain needs to be purchased separately (approx. $300/year)

Supported Model List (Below 80B)

Llama-3-70BQwen2.5-72B Mixtral-8x22B DeepSeek-V2.5 Phi-3.5 Yi-1.5 34B VLM: LLaVA-NeXT

6-12 Person Team

Package 2

$12,000 Hardware + $28,890 Platform/Service + $1,500 Interconnect

Total $42,390 / first year

Dedicated AI platform with 2nd-level domain
2× Blackwell G10 128GB + stacking cable
Supports open-source LLM / VLM below 80B (Dual-card acceleration)
Computing power reaches 2 hours/person/day @~30token/s
1-year local hosting (4 vCPU · 16GB RAM · 100GB · No GPU)