llama.cpp built-in web UI

ggml-org. tools/server/README.md checked 2026-10-12.

llama-server serves a web UI on the same host:port as /v1 (default 127.0.0.1:8080). Disable with --no-webui.

What it’s for

Fastest chat on the daily-driver server. No extra process.

Local endpoint

llama-server base: http://127.0.0.1:8080
Strata base: not documented — Strata is a different server; do not assume it ships this UI
Model name: The loaded GGUF (optional --alias)
API key: --api-key if you set one

Tool calling

Server README documents function calling / --tools. Completeness on Qwen3.6 is not measured here.

Long context

-c on the server. Our daily driver context is 262144; exact flags TODO.

ROCm / Radeon gotchas

This *is* the Vulkan (or HIP) process. Bind 127.0.0.1 unless you mean to share.

Hybrid local + cloud

No. This UI talks to the process you launched.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

llama.cpp built-in web UI → llama-server :8080

# Same process as /v1. Open http://127.0.0.1:8080
# Disable with: llama-server --no-webui
# Bind 127.0.0.1 unless you mean to share.

Daily-driver context is 262144; exact flags TODO in stacks.yaml.

llama.cpp built-in web UI → Strata

# not documented — Strata is a different server; do not assume it ships this UI.
# Open the llama-server UI on http://127.0.0.1:8080 instead, or use a chat harness against :8083/v1.

Strata web UI is not documented.