Ollama: Precision Revolution - New Float Formats and Testing Powerhouse
The Ollama team delivered three major improvements focused on precision and testing capabilities. Patrick Devine introduced support for cutting-edge float formats (mxfp4, mxfp8, nvfp4) that promise better model efficiency, while Daniel Hiltgen enhanced the testing infrastructure with individual model testing and comprehensive vision/tool calling stress tests. A Windows CI fix rounds out a solid day of platform improvements.
Duration: PT4M3S
Episode overview
This episode is a short developer briefing from Ollama.
It explains recent repository work in plain language.
- Show: Ollama
- Published: 2026-03-25T10:04:04Z
- Audio duration: PT4M3S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Hey there, fellow code explorers! Welcome back to another episode of the Ollama podcast. I'm your host, and wow, do we have some exciting updates to dive into today. Grab your favorite beverage because we're talking about some seriously cool advances in model precision and testing infrastructure.
You know what I love about today's updates? They're the perfect example of how great software evolves - we've got cutting-edge research meeting rock-solid engineering practices. Let me paint you the picture of what happened.
First up, Patrick Devine just landed something that's going to make AI enthusiasts everywhere do a little happy dance. We're talking about support for three new floating-point formats: mxfp4, mxfp8, and nvfp4. Now, if those sound like alphabet soup to you, here's the beautiful story behind them.
Think of these formats as different ways to store numbers in your models, kind of like choosing between different sized containers for your ingredients. The magic here is that Patrick's work lets you import models in bf16 format - that's bfloat16, which is already pretty efficient - and then convert them to these…
What makes this even cooler is the direct fp8 to mxfp8 conversion…
S…