# llama.cpp adds support for HTTP proxy environment variables

> The open‑source LLM runner now respects HTTP_PROXY, HTTPS_PROXY and NO_PROXY settings, fixing hangs behind corporate firewalls.

Oossa · 2026-10-16 · https://oossa.com/en/llama-cpp-adds-support-for-http-proxy-environment-variables

The llama.cpp project released version b11699 on 2026‑10‑16. It updates the common HTTP client to read the standard proxy environment variables. Downloads via the -hf flag and internal health checks now go through a configured proxy, or skip it for loopback addresses. Malformed proxy URLs are ignored, and a warning is printed. Documentation about proxy usage was moved to the server guide.

## The facts

- Release version b11699 published 2026‑10‑16
- Now honors HTTP_PROXY, HTTPS_PROXY and NO_PROXY env vars

## Why it matters

Users working behind corporate proxies can now download models and run llama.cpp without the previous “Loading model…” hang.

## Sources & references

1. [ggml-org/llama.cpp b11699](https://github.com/ggml-org/llama.cpp/releases/tag/b11699) – llama.cpp, 2026-10-16

Last updated: 2026-10-16