Using LlamaBarn with Claude Code

[erusev]

01 — Configure LlamaBarn

• Ensure LlamaBarn is running.
• Install the model(s) you want to use with Claude Code.
• Go to Settings and set the Context length to 32k tokens or more.

02 — Run Claude Code

Run claude with the following environment variables to point it to LlamaBarn:

ANTHROPIC_BASE_URL="http://localhost:2276" ANTHROPIC_API_KEY="dummy" claude --model gpt-oss-20b

Replace gpt-oss-20b with the ID of the model you want to use (right-click on model to get its ID).

Setting ANTHROPIC_API_KEY is required but its value doesn't matter.

Recommended models

• gpt-oss-20b — Requires Mac with 24GB+ memory
• gpt-oss-120b — Requires Mac with 96GB+ memory
• qwen3-coder — Requires Mac with 32GB+ memory