New Model Architecture and Image Generation Fixes
Ollama adds support for the LFM2 architecture with the new LFM2.5-1.2B-Thinking model, while also fixing crucial image generation bugs around model path resolution. The team merged 4 pull requests with significant architectural additions and important configuration fixes.
Duration: PT3M57S
Episode overview
This episode is a short developer briefing from Ollama.
It explains recent repository work in plain language.
- Show: Ollama
- Published: 2026-01-21T11:05:07Z
- Audio duration: PT3M57S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Hey there, amazing developers! Welcome back to another episode of the Ollama podcast. I'm so excited to be here with you on this beautiful January 21st, catching up on all the fantastic work that's been happening in our codebase. Grab your favorite beverage because we've got some really exciting updates to dive into…
So yesterday was absolutely buzzing with activity - we had four merged pull requests and some substantial changes that are going to make your Ollama experience even better. Let me paint you the picture of what's been happening.
The absolute star of the show has to be the addition of LFM2 architecture support. Jeffrey Morgan, with some fantastic collaboration from TommyBoiss, just merged a massive pull request that brings us LFM2.5-1.2B-Thinking model support. And when I say massive, I mean it - we're talking over 3,400 lines of new code…
What I love about this addition is how thoughtfully it's been implemented. They've added dedicated conversion logic, caching mechanisms, and even comprehensive test coverage. You can see files like `model/models/lfm2/cache.go` with 410 lines of carefully crafted caching logic, and a robust test suite with 444 lines…
Now, speaking of…
Jeffr…
Nearby episodes from Ollama
- Speed Boost and Model Magic
- Memory Magic and Command Makeover
- Making Ollama Play Nice with Everyone
- The Great Cleanup - Manifests Get Their Own Home
- New Model Support and Memory Management Wins
- FLUX.2 Image Generation Arrives
- Image Generation Goes Native and Parser Cleanup Magic
- Dynamic Loading and Experimental Models Take Center Stage