TheVibeFounder. Resource · Field Guide
Ollama · pick your local model

The local-model
picker, by your RAM.

Ollama runs open models locally: no cloud, no API bill, nothing leaves your machine. The hard part is picking the right one for your RAM, not the biggest one you've heard of. Here's the honest shortlist as of July 2026, what each is actually good at, the real download sizes, and the two commands to get serving.

Runs on · Mac · Windows · Linux Cost · free, fully local Serves at · localhost:11434 Sizes checked · ollama.com · Jul 2026
The 30-second version

What Ollama actually is

01

It runs open models on your own machine

Ollama is a one-command runner for open LLMs. Install it, run a model, and it downloads the weights and serves a local API. No cloud, no API key, nothing leaves your machine.

02

The model is really a RAM question

Every model is a download that has to fit in memory. The file size is the floor, and you want headroom on top for context and the OS. That is why the picker below is organised by RAM, not by benchmark.

03

One endpoint, almost any app

Once a model is running it speaks an OpenAI-compatible API at localhost:11434, so most AI apps and scripts can point at it with a one-line base-URL swap.

04

Free, but not frontier

Local models are genuinely useful and private, but a 12 to 32B model on your laptop is not GPT-5 or Claude Opus. Match the model to the task and you will be happy. Expect frontier quality and you will not.

The shortlist

Pick by your RAM

gemma4:12bThe default pick. Sees images, 256K context. 7.6 GB download.
16 GB
gpt-oss:20bThe flex. OpenAI's open model, benchmarked around o3-mini class at release. 14 GB, so it is tight on 16 GB. Close other apps.
16 GB
qwen3.6:27bThe serious tier. Strong agentic coder, 256K context. 17 GB.
32 GB+
deepseek-r1:32bThe reasoning specialist. Shows its full chain of thought. 20 GB.
32 GB+

Sizes are the actual Ollama downloads as of 16 Jul 2026. The RAM tier is the file plus headroom for context and the OS, so treat it as a floor, not a promise. On 16 GB, gemma4:12b is the comfortable pick and gpt-oss:20b works if you close memory-hungry apps.

Get it running

Three lines to a local model

1

Install Ollama

Download it from ollama.com for macOS, Windows, or Linux. It installs as a background service that is ready the moment it finishes.

2

Pull and run a model

ollama run gemma4 downloads the default pick and drops you straight into a chat. The first run pulls the weights, and after that it loads from disk instantly.

3

Point your apps at it

Ollama is now serving an OpenAI-compatible API at localhost:11434. Set that as the base URL in any app or script and you are running local.

# 1 · download Ollama from ollama.com (macOS / Windows / Linux)
ollama run gemma4                 # pull + chat with the default pick
# 2 · it is now serving at localhost:11434 (OpenAI-compatible)
curl localhost:11434/api/tags     # list the models you have pulled
The honest caveats

Before you expect too much

Download size is the floor, not the ceiling

A 7.6 GB model needs more than 7.6 GB of RAM once you add context and the OS. On 16 GB, stick to the smaller picks and close the memory-hungry apps.

Local is not frontier

These are excellent 12 to 32B models, not GPT-5 or Claude Opus. Great for drafts, code help, private data, and offline work. Weaker on long, hard reasoning chains.

First run is slow, then it is fast

The first ollama run downloads gigabytes. After that the model loads from disk and runs at your hardware speed, which on recent Apple Silicon is genuinely usable.

Quantized by default

Ollama ships quantized weights so models fit consumer RAM. That is the right trade for local use, but it is a small quality cut versus the full-precision cloud version.

Local vs. cloud

When to run it local

Run it local for

  • Private or sensitive data that should not leave your machine
  • Offline work: planes, trains, spotty wifi
  • High-volume, repetitive calls where API bills add up
  • Learning and building on an OpenAI-compatible API for free
  • Fast drafts, code help, and structured extraction

Just use the cloud for

  • The hardest reasoning, longest context, and frontier quality
  • Anything where a 12 to 32B ceiling is not enough
  • Machines under 16 GB of RAM
  • Big multimodal or agentic jobs that need a top-tier model
  • When your time is worth more than the API cost
One line to keep
The best local model
is the one that fits
your RAM.
The source · Ollama

Browse every model and its real size

The picker above is a snapshot. The full Ollama library lists every model, all its size variants, context windows, and whether it sees images, updated as new models land. Check the exact download before you pull.

ollama.com/library
Free · Mac · Windows · Linux · localhost:11434