Question 1

Does my data leave my network when using Llama?

Accepted Answer

No. Llama runs on hardware you control, so the prompts and the operational data stay inside your network. Use it where sending shipment or customer data to a third party is not permitted.

Question 2

What hardware do I need to run Llama?

Accepted Answer

It depends on the parameter size you choose. Ollama serves the same model family at several sizes, so a smaller variant runs on modest hardware while a larger one wants a dedicated GPU. Start small, measure answer quality on your own questions, and move up only if it falls short.

Question 3

Can I use Llama alongside a hosted provider?

Accepted Answer

Yes, and that is the common setup. Routine questions run locally on Llama while heavier analysis routes to a frontier provider, and routing falls back to the local model automatically when a hosted provider is rate-limited.

Question 4

Which Llama size should I run?

Accepted Answer

The small sizes run on a single workstation GPU and handle chat and drafting. Agent tool calling holds up better on the larger sizes, which need a server-class GPU. Start small and move up if tool-call accuracy falls short.

Question 5

Which other models can I run alongside Llama?

Accepted Answer

Any of them, and more than one at a time. CommerceShip runs ChatGPT, Claude, Gemini, Mistral, and Muse as frontier models, and DeepSeek, Gemma, GLM, Kimi, Llama, MiniMax, Nemotron, and Qwen as open-weight models, served through Ollama Cloud or on your own hardware. Route routine work to one model and heavier analysis to another, and if a provider is rate-limited or down, the run moves to a fallback and completes.

Question 6

What access does CommerceShip need to Llama?

Accepted Answer

The connection uses scoped credentials limited to the record types the integration works with, and you choose which fields are included. Credentials are encrypted at rest and stored separately from your operational data. Revoke the connection from either side at any time and the access ends with it.

Question 7

How is my data protected?

Accepted Answer

TLS in transit and AES-256 at rest, with tenant isolation enforced by row-level security in the database. Role-based permissions control who on your team can see cost data or change carrier settings, and automated actions are written to an audit log. CommerceShip is pursuing SOC 2 Type II certification. The security page carries the full detail.

Run supply chain AI locally with Llama

Llama Integration Capabilities

How the Llama integration works

Connect your Ollama

Assign Llama to the work

Ask and act

Llama Integration FAQs

Keep Llama inside your network

Other Models