llmpm — LLM Package Manager

LLM PACKAGE MANAGER

NPM for LLMs  |  Install, run & ship AI Models

Download and run 10,000+ free models from HuggingFace, Ollama & Mistral with a single command.

$pip install llmpm
$npm install -g llmpm
100K+
Models Available
3
Model Sources
5
Model Types
1
Command to Start

QUICK START

From install to running a model in under a minute.

sh
#Install the model
$llmpm install Qwen/Qwen2.5-0.5B-Instruct
$
#Run it interactively
$llmpm run Qwen/Qwen2.5-0.5B-Instruct
$
#Serve as OpenAI-compatible API
$llmpm serve Qwen/Qwen2.5-0.5B-Instruct

SEE IT IN ACTION

Watch llmpm install and run a model end-to-end in seconds.

loading video...

COMMANDS

Everything you need to manage large language models.

Install Models

Install any model from HuggingFace, Ollama, or Mistral with a single command.

$llmpm install Qwen/Qwen2.5-0.5B-Instruct

Run Instantly

Auto-detects model type and launches the right backend. Text, image, audio — it just works.

$llmpm run Qwen/Qwen2.5-0.5B-Instruct

Serve as API

Expose any model as an OpenAI-compatible REST API with a built-in chat UI.

$llmpm serve Qwen/Qwen2.5-0.5B-Instruct

Push Models

Upload fine-tuned models directly to HuggingFace Hub with one command.

$llmpm push my-org/my-fine-tune

SUPPORTED MODEL TYPES

One tool for every modality.

💬
Text Generation
GGUF via llama.cpp & Transformer checkpoints
🎨
Text-to-Image
Diffusion models via Diffusers
👁️
Vision Models
Image-to-text, captioning & VQA
🎤
Speech-to-Text
ASR with Whisper and more
🔊
Text-to-Speech
TTS generation to WAV output

Start in 30 seconds.

No config files, no complex setup. Just install and run.