Free AI access

Surprisingly, many people have still never talked to a neural network or run a single AI agent - it seems expensive, complex, or 'not for me'. In fact you can start for free right now, often without a bank card or a powerful computer. Below are proven ways to get access to AI: from free tiers to compute grants. Limits and terms change - we check them regularly.

How to use: pick a card, open the link and sign up - current limits are listed on each one.

Free tiers

Work instantly and for free, usually without a card: sign up and use. There are limits (requests per day, tokens per minute), but they're plenty to get started and for personal tasks.

Google AI Studio
no card
1,500 requests/day, 1M context

Gemini 2.5/3 Flash, Gemma 3, multimodal

aistudio.google.com
Open →
Groq
no card
6k tokens/min, 300 t/s

Llama 3.3 70B, Qwen, DeepSeek

console.groq.com
Open →
Cerebras
no card
1M tokens/day, up to 2300 t/s

Llama 3.3 70B

cloud.cerebras.ai
Open →
NVIDIA NIM
no card
~40 requests/min, ~80-100 models

DeepSeek R1/V3, Llama, Qwen

build.nvidia.com
Open →
OpenRouter
no card
50 requests/day (1,000 after a one-time $10)

28-30 free models through one key

openrouter.ai
Open →
GitHub Models
no card
Limit by Copilot plan (~50/day on top models)

GPT-5, GPT-4.1, GPT-4o, o4-mini, Llama

github.com
Open →

Trial credits

A starting balance in dollars to try out (e.g. $5). Expires in a few days or weeks - handy to test a model for your task before paying.

Anthropic
no card
$5 in credits, expire in 14 days

No card, SMS sign-up

console.anthropic.com
Open →
Together AI
No free tier, prepay from $5

Wide open-model catalog

api.together.ai
Open →
SambaNova
no card
$5 in credits, 30 days

No card

cloud.sambanova.ai
Open →
Google Vertex AI Free Trial
no card
$300 in 90-day credits

New Google Cloud accounts; spend on Gemini 3.1 Pro, Imagen, Veo, full Vertex AI catalog

cloud.google.com
Open →

Startup programs

Large compute grants and credits for companies: from thousands to hundreds of thousands of dollars. How to get it: register a startup (legal entity, product, site) and apply; some programs require an accelerator or an investor.

OpenAI Codex for OSS
$1,200 (6 mo ChatGPT Pro + Codex)

For open-source maintainers

openai.com
Open →
Anthropic for Startups
$1k-$100k in credits

Application-based

anthropic.com
Open →
OpenAI Grove
Up to $50k

Residency in San Francisco

openai.com
Open →
Google for Startups AI-First
Up to $350k over 2 years

Via accelerator/VC

cloud.google.com
Open →
NVIDIA Inception
Up to $100k DGX Cloud + NIM

For companies

nvidia.com
Open →
AWS Activate
$1k-$200k in infra credits

Application-based

aws.amazon.com
Open →

For students

Free access and credits with student status. How to get it: confirm you're a student - a .edu email or verification via GitHub Education and university programs.

OpenAI Codex for Students
$100 (2,500 credits)

Students in US/Canada

openai.com
Open →
Cursor Pro for Students
Free for one year (~$240)

.edu email in North America

cursor.com
Open →
GitHub Education
Copilot, JetBrains, Replit, Perplexity free

Verified students

education.github.com
Open →
Azure for Students
$100 in credits

University email

azure.microsoft.com
Open →
YC AI Student Starter Pack
no card
$25,000+ in cloud credits, AI model credits, free tools

Free credits for students attending YC campus events 2025-2026; includes Azure/AWS cloud, GPT/Claude/Grok, voice, search, video, databases

deals.ycombinator.com
Open →
Thunder Compute Student Program
no card
$20 in GPU credits

Free A100 compute credits with verified .edu email for students; 3–14 day activation

thundercompute.com
Open →
Pick your hardware

Local AI: your own model on your own hardware

Open models can run right on your computer - free, offline, and your data never leaves it. Below, in plain words, we figure out what your machine can handle and pick a model you install with a single command.

How to check your hardware2 minutes and you know your class.

An AI model is a large file that loads entirely into your computer's memory to run. The smarter the model, the bigger it is and the more memory it needs. Simple rule: the number in a model's name (e.g. 7B = 7 billion parameters) is roughly how many gigabytes of memory it needs; in the compact Q4 format that's about half (7B ≈ 4-5 GB). A model runs fastest on a graphics card, in its video memory (VRAM); without a strong GPU it runs on regular RAM - slower, but it works. Macs with M1-M4 chips use shared memory, so they handle even large models well. First, find out how much memory you have:

System memory (RAM) - every computer has it
  • Mac: Open the Apple menu (logo in the top-left of the screen) and choose About This Mac. The Memory line shows your amount - for example, '16 GB'.
  • Windows: Press `Ctrl+Shift+Esc` together, open the Performance tab and pick Memory on the left. The total is shown at the top - for example, '16.0 GB'.
  • Linux: In a terminal, type `free -h` and press Enter. On the `Mem` line, the first number is your total RAM.
Video memory (VRAM) - your graphics card
  • NVIDIA: In a terminal, type `nvidia-smi` - the VRAM size is in the top-right of the table. Or check it in the GeForce Experience app.
  • AMD: On Linux use `radeontop`; on Windows check the AMD Adrenalin app.
  • Windows: Press `Ctrl+Shift+Esc` -> Performance -> GPU. Find the 'Dedicated GPU memory' line - this works for any card.
  • Mac (M1-M4): There is no separate VRAM - it uses the computer's shared memory, which is a plus: almost all of it can go to AI.
How to pick a model for your memory

Take a model whose size (in Q4, shown on the card) is smaller than your free memory, and leave 2-4 GB spare - for the system and the 'conversation memory' (context). Not sure? Start with a smaller model: if it runs snappy, try a bigger one. We've already sorted the models into tiers below - just pick your memory size.

Entry-level laptops, base MacBook Air M1/M2, PCs without a GPU.

Llama 3.2 3B
recommended
~2 GBContext: 128KLlama 3.2

Best pick for weak hardware: fast, keeps a conversation well and follows instructions.

Install
Phi-4 Mini
~2.5 GBContext: 128KMIT

Strong at reasoning and code for its size, commercial-friendly (MIT).

Install
Gemma 2 2B
~1.6 GBContext: 8KGemma

The lightest: runs almost anywhere, good for simple tasks and notes.

Install

How to run it

LM StudioDownload

LM Studio - a GUI app: install it, pick a model from the list, click download and chat. Easiest to start, no command line.

Ollama - command-line: a single `ollama run <model>` downloads and runs the model. Great for developers and integrations (a local API on localhost).

Model comparison

These are just examples for local use. Browse and compare every model in the full catalog: All models · Compare models

ModelTierSize (Q4)
Llama 3.2 3B8 GB RAM~2 GB
Phi-4 Mini8 GB RAM~2.5 GB
Gemma 2 2B8 GB RAM~1.6 GB
Llama 3.1 8B16 GB RAM~4.9 GB
Qwen2.5 7B16 GB RAM~4.7 GB
Mistral NeMo 12B16 GB RAM~7 GB
Qwen2.5 Coder 32B32 GB RAM / VRAM~20 GB
Gemma 2 27B32 GB RAM / VRAM~16 GB
DeepSeek R1 32B32 GB RAM / VRAM~20 GB
Llama 3.3 70B64 GB+ RAM / VRAM~43 GB
Qwen2.5 72B64 GB+ RAM / VRAM~47 GB
DeepSeek R1 70B64 GB+ RAM / VRAM~43 GB

FAQ

What is quantization and Q4?

Quantization shrinks a model by lowering weight precision - the file gets several times smaller and fits in memory. Q4 (4-bit) is a popular balance: near-full quality at about half the size of Q8. Sizes in this guide are for Q4.

RAM vs VRAM - which matters?

On a GPU the model runs fastest - here VRAM size matters. Without a strong GPU the model loads into regular RAM and runs on the CPU (slower, but works). Apple Silicon has unified memory, so Macs handle large models well.

Can I use these commercially?

Check the model license. Apache 2.0 and MIT allow commercial use with almost no limits. Llama and Gemma licenses also allow it but with conditions (e.g. a user-count cap for Llama). Always read the license text.

How much disk space do I need?

Each model is a separate file from ~1.5 GB (light) to 40+ GB (large). Leave spare room for several models. Ollama and LM Studio keep them in their own folder; you can delete unused ones with one command.