cd /news/developer-tools/run-a-private-openai-compatible-llm-… · home topics developer-tools article
[ARTICLE · art-118490] src=dev.to ↗ pub= topic=developer-tools verified=true sentiment=· neutral

Run a private OpenAI-compatible LLM endpoint on Apple Silicon with one Rust binary

A developer has released Ferrum, an MIT-licensed Rust-based local LLM inference server that provides a private OpenAI-compatible endpoint on Apple Silicon. The tool, installable via Homebrew, supports models like Qwen3.5 and includes a 'doctor' command to check setup prerequisites. The developer is seeking feedback from Apple Silicon users on potential issues.

read1 min views1 publishedSep 2, 2026

Disclosure: I maintain Ferrum, an MIT-licensed local LLM inference server written in Rust.

If you want a private OpenAI-compatible endpoint on an M-series Mac without setting up Python or a container, this is the shortest path I currently recommend.

The commands below were tested end to end with the published Ferrum v0.8.3 Homebrew build on an M1 Max.

brew tap sizzlecar/ferrum
brew install ferrum
ferrum doctor qwen3.5:4b-q4_k_m

ferrum doctor

checks the local setup before inference. In one real install it caught missing Xcode Command Line Tools before the user reached a harder-to-diagnose failure.

The first run downloads about 2.55 GiB. The terminal can look quiet during that download, so give it time before assuming it has hung.

ferrum run qwen3.5:4b-q4_k_m --disable-thinking

Qwen3.5 emits verbose reasoning by default. --disable-thinking

gives a more conventional first-chat experience. Omit the flag when you want the reasoning behavior.

ferrum serve \
  --model qwen3.5:4b-q4_k_m \
  --served-model-name ferrum \
  --disable-thinking \
  --port 8000

In another terminal:

curl http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "ferrum",
    "messages": [{"role": "user", "content": "Reply exactly: ferrum-ok"}],
    "max_tokens": 32
  }'

A working setup returns HTTP 200 with a non-empty assistant response.

I am looking for failure-oriented feedback from Apple Silicon users:

doctor

, the model download, or the first API request fail?Repository and issue tracker: github.com/sizzlecar/ferrum-infer-rs

This post was drafted with assistance from OpenAI Codex. The commands and stated behavior were checked against the published build; no comparative performance claim is being made here.

── more in #developer-tools 4 stories · sorted by recency
── more on @ferrum 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/run-a-private-openai…] indexed:0 read:1min 2026-09-02 ·