iwant

iwant is a command-line tool that launches open weights models on cloud GPUs with OpenAI-compatible endpoints.

This command-line tool launches open weights models on bare metal cloud GPUs directly in a user cloud account. It rents the GPU, configures the server, downloads weights, and waits until the model API responds. Users receive an OpenAI-compatible endpoint, an API key, and SSH access. It supports multiple models such as gpt-oss-20b, deepseek-v4-flash, and mimo-v2.6-flash using specific hardware recipes. The tool runs on Google Cloud Platform, requiring an active project with billing, quotas, and capacity.

iwant at a glance

Best for: Software engineer
Runs on: CLI, Web
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: github.com/narevai/iwant

Key features

Launch open models with a single command
Provide OpenAI-compatible API endpoints
Include SSH access to running clusters
Offer an interactive model picker
Tear down clusters easily
Check cloud credentials and show login guidance
List current deployments and endpoints

Use it for

Deploying open weights models on cloud GPUs
Running custom model inference via OpenAI-compatible apps
Managing cloud GPU infrastructure through a command line
Accessing remote servers via SSH for debugging

Companions

Tools that articles about iwant recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to iwant

GPUStack — Unifies AI model serving and GPU compute management across heterogeneous hardware.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
Union.ai — Runs machine learning tasks natively on Apple Silicon GPUs using Metal.
Strata — Runs large AI models locally on consumer gaming PCs without server reliance.
ScaledThought — Access open-weight models on an OpenAI-compatible API set up entirely by an AI agent.
AirLLM — Runs massive 70B+ parameter models on small 4GB consumer GPUs.
fal — Access 1,000+ generative models and high-performance serverless GPUs.
TensorRT — Speeds up inference by 36X compared to CPU-only platforms.
openGym — Zero subscriptions, accounts, or telemetry, with support for bring-your-own AI coaching.
Replicate — Run and fine-tune thousands of open-source and custom AI models via a single cloud API.
Imp — Runs local models directly on NVIDIA Blackwell hardware using native 4-bit math.
Freebuff — Access multiple coding AI models for free without subscriptions.

All iwant alternatives