LFM2.5-local
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
LFM2.5 — On-Device AI Chat & MCP Server
Run Liquid AI's LFM2.5-1.2B-Instruct model locally on your Mac with a beautiful chat interface and MCP integration for tools like Claude Desktop, Cursor, and OpenClaw.
~120 tok/s on Apple Silicon · ~480 tok/s across 4 Macs · 1.5 GB RAM · 100% Private & Offline
✨ Features
🖥️ Beautiful Chat UI — Dark-themed, responsive chat interface with markdown rendering, code highlighting, and real-time performance metrics
⚡ MLX Acceleration — Runs natively on Apple Silicon via MLX with 8-bit quantization
🔌 MCP Server — Expose LFM2.5 as tools for Claude Desktop, Cursor, OpenClaw, and any MCP-compatible client
🔀 Multi-Mac Cluster — Distribute inference across multiple M4 Macs with automatic load balancing and failover
📊 Live Stats — Token count, generation speed (tok/s), and response time displayed in real-time
🎯 Quick Prompts — Pre-built prompts for common tasks (CRISPR explanation, code architecture, creative writing, data analysis)
Related MCP server: local-mcp
🏗️ Architecture
Single-Mac Mode:
Client → MLX Server (:8080)
Cluster Mode (4× throughput):
Client → Cluster LB (:5200) → Mac 1 MLX (:8080)
→ Mac 2 MLX (:8080)
→ Mac 3 MLX (:8080)
→ Mac 4 MLX (:8080)🚀 Quick Start
Prerequisites
1. Install
# Clone the repo
git clone https://github.com/WispAyr/LFM2.5-local.git
cd LFM2.5-local
# Install MLX dependencies (if needed)
pip install mlx-lm
# Install MCP dependencies
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt2. Run
# Just the MLX server + chat UI
./start_server.sh
# MLX + MCP server (for Claude Desktop, Cursor, OpenClaw)
./start_server.sh --mcp
# Everything (MLX + MCP + web UI)
./start_server.sh --all
# Multi-Mac cluster (MLX + Load Balancer + MCP + web UI)
./start_server.sh --cluster3. Open
Service | URL | Description |
Chat UI | Web chat interface | |
MLX API | OpenAI-compatible API | |
Cluster LB | Load-balanced API (cluster mode) | |
Cluster Status | Live node health | |
MCP Server | MCP protocol endpoint |
🔌 MCP Integration
The MCP server exposes LFM2.5 as tools that any MCP-compatible client can call.
Tools
Tool | Description |
| General-purpose chat — questions, reasoning, writing |
| Summarize text with configurable length |
| Code review, bug detection, suggestions |
| Translate text to any language |
Resources
URI | Description |
| Model architecture, specs, capabilities |
| Live MLX server connection status |
Prompts
Prompt | Description |
| Structured code review template |
| ELI5-style concept explanation |
Connect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"lfm25": {
"command": "/path/to/LFM2.5-local/.venv/bin/python3",
"args": ["/path/to/LFM2.5-local/mcp_server.py"]
}
}
}Connect to Cursor
Settings → MCP Servers → Add and paste the same config.
Connect to OpenClaw
Point to http://localhost:5100/mcp as an MCP server endpoint.
📁 Project Structure
├── index.html # Chat web UI (single-file, no build step)
├── mcp_server.py # FastMCP server with tools, resources, prompts
├── cluster.py # Multi-Mac cluster load balancer
├── cluster_config.json # Cluster node configuration
├── server.py # Web UI proxy server (serves static + proxies API)
├── mcp_config.json # MCP config template for Claude Desktop / Cursor
├── start_server.sh # Launcher script (--mcp, --all, --cluster flags)
├── demo_lfm25.py # Python demo script
└── requirements.txt # Python dependencies🔀 Multi-Mac Cluster
Distribute inference across multiple M4 Macs for ~480 tok/s combined throughput and automatic failover.
Setup
1. On each Mac, start the MLX server:
pip install mlx-lm
python3 -m mlx_lm.server --model LiquidAI/LFM2.5-1.2B-Instruct-MLX-8bit --port 8080 --host 0.0.0.02. Edit cluster_config.json on your primary Mac with each node's IP:
{
"nodes": [
{"name": "Mac-1", "host": "192.168.1.10", "port": 8080, "weight": 1},
{"name": "Mac-2", "host": "192.168.1.11", "port": 8080, "weight": 1},
{"name": "Mac-3", "host": "192.168.1.12", "port": 8080, "weight": 1},
{"name": "Mac-4", "host": "192.168.1.13", "port": 8080, "weight": 1}
]
}3. Start the cluster:
./start_server.sh --clusterFeatures
Least-loaded routing for POST requests, round-robin for GETs
Health checking every 5 seconds with automatic failover
SSE streaming passthrough for real-time token generation
Node weights for prioritizing faster Macs
Status dashboard at
/cluster/statuswith per-node metrics
🧠 About LFM2.5
LFM2.5 is not a Transformer. It's a hybrid architecture from Liquid AI combining:
10× Gated Short Convolution layers — fast sequential processing
6× Grouped Query Attention layers — selective attention
This gives it a unique performance profile: extremely fast inference (~120+ tok/s on M-series Macs) with a small 1.17B parameter footprint.
Spec | Value |
Parameters | 1.17B |
Layers | 16 |
Context | 32K tokens |
Vocab | 65,536 |
Training | 28T tokens |
Quantization | 8-bit (MLX) |
📄 License
MIT
🔗 Links
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Related MCP Servers
- FlicenseAqualityDmaintenanceLocal multimodal MCP server for vision, document, audio, video, and GUI automation, all processed locally on Apple Silicon for privacy and security.9-
- FlicenseNot gradedqualityDmaintenanceEnables running MCP tools against local MLX models on your Mac, with hardware-aware configuration, CLI streaming, and a dashboard for routing and monitoring.5,198 npm-
- AlicenseNot gradedqualityDmaintenanceMCP server that enables local Apple on-device Foundation Model access via any MCP client, supporting text generation, structured output, and multi-turn chat on macOS.2MIT
- AlicenseNot gradedqualityBmaintenanceLocal voice and AI platform for macOS offering speech recognition, speech synthesis, MLX-based inference, OpenAI-compatible APIs, and MCP tools for use as an assistant or integration gateway.MIT