I distilled my first model in 2021 and failed miserably. After years of trial and error, I've developed a counterintuitive approach to model distillation that delivers smaller, faster models without sacrificing performance. Here's my step-by-step process.
The Framework That Actually Works
Here is a simple framework for evaluating model distillation. It's not complicated, but it requires discipline.
Step 1: the data tells a different story than your gut
This is where most people go wrong. They skip this step entirely and jump straight to execution. Don't do that.
Step 2: customer feedback is the only metric that matters
Once you have the foundation right, this becomes much easier. I've watched founders struggle with this for months when the answer was staring them in the face.
Step 3: Iterate relentlessly
Nothing works perfectly the first time. The companies that get model distillation right treat it as an ongoing process, not a one-time project.
Why Most Approaches Fail
Many common approaches to model distillation are flawed at the root.
The root cause is usually one of three things:
Copying what big companies do without understanding why they do it. What works for Google doesn't work for a 10-person startup.
Over-engineering the solution when a simple approach would work better. I've seen teams spend six months building something that could have been done in two weeks.
Ignoring the human element. Technology is the easy part. Getting people to actually use it is where the real challenge lives.
The Reality Nobody Talks About
A lot of the advice on model distillation rests on assumptions that made sense five years ago. The world has moved on.
The first thing to understand is that you need to move fast and break things. I've seen this play out across dozens of companies. The pattern is unmistakable.
Many teams spend months on the wrong path before realizing that most founders overthink this and underspend on execution. Once they make the switch, everything changes.
The AI Angle
Any discussion of model distillation in 2026 has to include AI. As someone who's invested in Anthropic, OpenAI, Scale AI, and Hugging Face, I have a front-row seat to how AI is transforming this space.
The short version: AI makes good practitioners better and bad practitioners worse. It's an amplifier, not a replacement.
Some teams use AI to get far more out of model distillation. Others spend heavily on AI that solves the wrong problem. The difference comes down to understanding what you're actually trying to achieve.
This connects to broader themes around small language models, on-device AI, model distillation that I've been thinking about a lot lately.
Wrapping Up
I've shared a lot here, and I know it can feel overwhelming. But you don't need to get model distillation right on day one. You just need to get started and keep improving.
Founders who do well at model distillation tend to share one trait: they're relentlessly practical. They don't chase perfection. They chase progress.
That's the mindset I'd encourage you to adopt. Start where you are. Use what you have. Do what you can. And keep pushing forward.
As always, I'm rooting for you.
Frequently Asked Questions
Q:Who is this guide designed for?
This guide is written for founders and operators who want practical, actionable advice rather than theoretical frameworks. Whether you're just starting out or scaling an existing business, the principles here apply across stages.
Q:Is this guide based on real experience?
Every recommendation in this guide comes from direct experience, either from building and selling my own companies, or from patterns I've observed across 234 angel investments. I don't write about things I haven't personally tested.
Q:What if I disagree with some of the advice?
Good. That means you're thinking critically, which is exactly what a good founder should do. Take what resonates, test it, and discard what doesn't work for your specific situation. No advice is universal.
Q:How should I work through this guide?
Don't try to absorb everything in one sitting. Read through once to get the big picture, then go back and work through each section as it becomes relevant to your current challenges. Bookmark it and return to it regularly.