Ollama cheat sheet

A scannable Ollama reference: 11 short snippets across 7 topics, each linking back to the lesson it came from.

At a glance

Topic	What it covers
Running models locally	Quantisation (the q4, q5 suffixes) trades a small amount of quality for large memory savings. q4_K_M is the common	lesson
Calling Ollama from code	Embed locally, then rank with cosine similarity. This gives you private semantic search with no per-query cost — the	lesson
Choosing and evaluating models	Public benchmarks measure general ability on someone else's data. What matters is whether the model does your job	lesson
The Modelfile and custom models	Write a Modelfile with FROM, SYSTEM, TEMPLATE and PARAMETER, set a reusable system prompt, and build a custom model	lesson
Model tags, sizes and quantisation explained	The model:tag convention, parameter counts, Q4/Q5/Q8 and FP16 variants, VRAM versus RAM, and pinning tags so a	lesson
Performance tuning	keep_alive, concurrency and model-load limits, context and output caps, GPU offload, and measuring tokens per second	lesson
Serving Ollama in Docker and over a network	Container images, GPU passthrough, volumes for models, OLLAMA_HOST binding, reverse proxies, and access control that is	lesson

Quick snippets

Running models locally

Install and pull

# macOS / Linux
curl -fsSL https://ollama.com/install.sh | sh

# then, in any shell
ollama pull llama3.2          # downloads weights, cached for later runs
ollama run llama3.2           # interactive chat
ollama list
ollama ps                     # what is loaded in memory right now

Serving more than one request

# allow more parallel requests and keep the model resident
OLLAMA_NUM_PARALLEL=4 OLLAMA_MAX_LOADED_MODELS=2 OLLAMA_KEEP_ALIVE=30m ollama serve

Full lesson: Running models locally →

Calling Ollama from code

The HTTP API

curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "Explain HTTP caching in two sentences.",
  "stream": false
}'

The HTTP API

import requests

def ask(prompt, model="llama3.2", **opts):
    r = requests.post("http://localhost:11434/api/generate",
                      json={"model": model, "prompt": prompt,
                            "stream": False, "options": opts},
                      timeout=120)
    r.raise_for_status()
    return r.json()["response"]

print(ask("Summarise this ticket in one line.", temperature=0.1))

Embeddings for search

r = requests.post("http://localhost:11434/api/embed",
                  json={"model": "nomic-embed-text", "input": ["first doc", "second doc"]})
vectors = r.json()["embeddings"]

import numpy as np
def cosine(a, b):
    a, b = np.array(a), np.array(b)
    return float(a @ b / (np.linalg.norm(a) * np.linalg.norm(b)))

Full lesson: Calling Ollama from code →

Choosing and evaluating models

Evaluate on your own inputs

cases = [
    ("Refund my £40 order #A-1042", "refund"),
    ("How do I reset my password?", "how_to"),
    ("Your app deleted my files!!", "escalate"),
]

for model in ["llama3.2", "qwen2.5:7b", "phi4"]:
    ok = 0
    for text, expected in cases:
        got = ask(f"Classify as one of refund|how_to|escalate:\n{text}", model=model).strip()
        ok += (got == expected)
    print(model, f"{ok}/{len(cases)}")

Routing and fallback

def answer(prompt):
    out = ask(prompt, model="llama3.2", temperature=0.1)
    if not is_confident(out):            # your own check, e.g. missing fields
        out = ask(prompt, model="qwen2.5:14b")   # escalate
    return out

Full lesson: Choosing and evaluating models →

The Modelfile and custom models

Writing a Modelfile

# validate before building
ollama create support-bot -f ./Modelfile
ollama run support-bot
ollama show support-bot --modelfile      # print the resolved Modelfile
ollama show support-bot --parameters     # the effective parameter values

Full lesson: The Modelfile and custom models →

Model tags, sizes and quantisation explained

Quantisation levels

# compare two quantisations of the same model on the same prompt
ollama run qwen2.5:7b-instruct-q4_K_M "Explain a database index in one sentence."
ollama run qwen2.5:7b-instruct-q8_0  "Explain a database index in one sentence."

# measure throughput rather than guessing
ollama run qwen2.5:7b-instruct-q4_K_M --verbose "Write a 200-word product description."
# the response reports eval rate (tokens/s) and prompt eval rate

Full lesson: Model tags, sizes and quantisation explained →

Performance tuning

Server-side settings

# environment variables read by the ollama server at startup
OLLAMA_KEEP_ALIVE=30m          # keep a model resident for 30 minutes after last use
OLLAMA_NUM_PARALLEL=4          # concurrent requests per model
OLLAMA_MAX_LOADED_MODELS=2     # how many models may be resident at once
OLLAMA_MAX_QUEUE=512           # requests queued before rejecting new ones
OLLAMA_NUM_GPU=1               # GPUs to use on a multi-GPU host
OLLAMA_FLASH_ATTENTION=1       # lower KV-cache memory on supported hardware
OLLAMA_HOST=127.0.0.1:11434    # bind address

ollama serve

Full lesson: Performance tuning →

Serving Ollama in Docker and over a network

Binding and access control

# bind to all interfaces, then protect it with a reverse proxy
OLLAMA_HOST=0.0.0.0:11434 ollama serve

Full lesson: Serving Ollama in Docker and over a network →

FAQ

Is this Ollama cheat sheet free to use?

Yes. No sign-up and no tracking: the page is static, every example is on the page itself, and you can print it or save it as a one-page reference.

Where do the examples come from?

Every snippet is taken from the 7 lessons of the Ollama course on this site, and each section links back to the lesson it was pulled from.

How do I go deeper than a cheat sheet?

Open the full Ollama course — it carries the worked explanations, the edge cases and the exercises behind every line here.

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow

Last refreshed 2026-09-27.