[PR #1149] [CLOSED] docs: add Rapid-MLX to local server options #1146

New issue

Closed

opened 2026-10-18 14:17:29 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:17:29 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/1149
Author: @raullenchai
Created: 3/21/2026
Status: ❌ Closed

Base: main ← Head: feat/add-rapid-mlx-local-server

📝 Commits (1)

bb51aa6 docs: add Rapid-MLX to local server options

📊 Changes

1 file changed (+25 additions, -0 deletions)

View changed files

📝 docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx (+25 -0)

📄 Description

Summary

Adds Rapid-MLX as a new local server option in the OpenAI-compatible providers documentation page
Placed alongside existing local servers (Llama.cpp, LM Studio, vLLM, LocalAI, Docker Model Runner)
Follows the exact same TabItem format used by other entries

What is Rapid-MLX?

Rapid-MLX is an OpenAI-compatible inference server optimized for Apple Silicon (MLX). Key features:

2-4x faster than Ollama on Apple Silicon
Full tool calling support
Built-in reasoning separation for thinking models
Prompt caching for faster follow-up responses
Drop-in compatible with Open WebUI via http://localhost:8000/v1

Connection details

Setting	Value
URL	`http://localhost:8000/v1`
API Key	Leave blank

Test plan

Verify MDX renders correctly (tab appears in Local Servers section)
Verify install commands work
Verify connection URL works with Open WebUI

🤖 Generated with Claude Code

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/docs/pull/1149 **Author:** [@raullenchai](https://github.com/raullenchai) **Created:** 3/21/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feat/add-rapid-mlx-local-server` --- ### 📝 Commits (1) - [`bb51aa6`](https://github.com/open-webui/docs/commit/bb51aa6528052dc6a63b110b78b1f948679e88ee) docs: add Rapid-MLX to local server options ### 📊 Changes **1 file changed** (+25 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx` (+25 -0) </details> ### 📄 Description ## Summary - Adds **Rapid-MLX** as a new local server option in the OpenAI-compatible providers documentation page - Placed alongside existing local servers (Llama.cpp, LM Studio, vLLM, LocalAI, Docker Model Runner) - Follows the exact same TabItem format used by other entries ## What is Rapid-MLX? [Rapid-MLX](https://github.com/raullenchai/Rapid-MLX) is an OpenAI-compatible inference server optimized for Apple Silicon (MLX). Key features: - **2-4x faster** than Ollama on Apple Silicon - Full **tool calling** support - Built-in **reasoning separation** for thinking models - **Prompt caching** for faster follow-up responses - Drop-in compatible with Open WebUI via `http://localhost:8000/v1` ## Connection details | Setting | Value | |---|---| | **URL** | `http://localhost:8000/v1` | | **API Key** | Leave blank | ## Test plan - [ ] Verify MDX renders correctly (tab appears in Local Servers section) - [ ] Verify install commands work - [ ] Verify connection URL works with Open WebUI 🤖 Generated with [Claude Code](https://claude.com/claude-code) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:17:29 +00:00