Open Source Models

Suman SharmaSuman Sharma

A closed API is faster to ship. An open model is what I want when data cannot leave the building, or when per-token pricing will not work at the volume I expect.

“Open” still means read the license. Some weights are free to try and not free to ship in a product.

Developer workspace — running a model yourself is still software operations

Open vs closed

Closed APIOpen weights
StartAn API keyA download and a runtime
DataLeaves your server unless the contract says otherwiseStays where you run it
QualityOften the best general chatVaries. Test your task
OpsTheir uptime, their price changesYour GPUs, your patches

Popular open source models change every few months. I do not memorize the leaderboard. I keep a short list for chat, embeddings, and speech, and I re-benchmark when I am about to commit.

Finding them

Hugging Face is the index I use.

  • Hugging Face Hub — model cards, files, licenses, and how people actually run the model
  • Hugging Face Tasks — filter by what you need: text generation, feature extraction, automatic speech recognition, text-to-image
  • Using open source models — read the card before you celebrate. “Open” and “commercially usable” are not the same sentence

How I run them

Pick the smallest runtime that matches where the feature lives:

  • Inference SDK / hosted inference — someone else runs the weights, you still get an API. Less ops, less privacy than local.
  • Ollama — local chat models for development and for products that must stay on device or on your VPC. Ollama models are a curated set. The Ollama SDK is enough for a first integration.
  • Transformers.js — when the model should run in the browser or in Node without Python. Good for small models. A bad idea for a 70B chat model.

A rule I use

If the feature is a prototype and the data is not sensitive, I use a closed API. If a lawyer or a customer contract says prompts stay in our network, I move that path to an open model and I accept the quality trade until evals say otherwise.

Next

Search by meaning starts with vectors, not with a bigger chat model:

Frequently asked questions

What is the difference between open and closed source models?

Closed models are called over a vendor API. You do not get the weights. Open models publish weights you can download and run, with a license you still have to read.

What is Ollama?

A simple way to download and run open models on your own machine, with a small SDK for apps that should work without sending every prompt to a third party.

When should I use Hugging Face?

When I am searching for a model by task — chat, embeddings, speech, image — and I need the files, the license, and a way to run inference.

Contact

Get in Touch

Want to call me? book a call and I'll respond in the available time slot. I will ignore all soliciting.