Ollama Now Runs Faster on Macs Thanks to Apple's MLX Framework - MacRumorsOpen MenuShow RoundupsShow Forums menuVisit ForumsOpen Sidebar
Skip to Content

Ollama Now Runs Faster on Macs Thanks to Apple's MLX Framework

Ollama, the popular app for running AI models locally on a computer, has released an update that takes advantage of Apple's own machine learning framework, MLX. The result is a hefty speed boost on Macs with Apple silicon.

ollama logo mac
According to Ollama, the new version processes prompts around 1.6 times faster (prefill speed) and nearly doubles the speed at which it generates responses (decode speed). Macs with M5-series chips are said to see the largest improvements, thanks to Apple's new GPU Neural Accelerators.

The update also includes smarter memory management, which should make AI-powered coding tools and chat assistants feel noticeably more responsive during extended use.

Ollama says the new performance boost should especially benefit macOS users who run personal assistants like OpenClaw or coding agents like Claude Code, OpenCode, or Codex.

The preview release is available to download as Ollama 0.19 – just make sure you have a Mac with more than 32GB of unified memory to run it. Support is currently limited to Alibaba's Qwen3.5, but Ollama says support for more AI models is planned.

Popular Stories

Apple Event Logo

Apple Working on All-New Operating System

Wednesday July 29, 2026 11:39 am PDT by
Apple is developing an all-new operating system that is essentially a mix of tvOS, watchOS, and iOS, according to Bloomberg's Mark Gurman. In a report this week, he said the operating system will feature a grid of icons, widgets, and apps, along with customizable clock faces. The new software platform is intended for Apple's long-rumored smart home hub. With built-in facial recognition,...
imac video apple feature

Apple Made Its Second-Biggest Acquisition Ever This Year

Wednesday July 29, 2026 12:03 pm PDT by
Apple this year acquired Israeli startup Q.ai for close to $2 billion, according to the Financial Times. That would make this Apple's second-biggest acquisition ever, after it paid $3 billion for the popular headphone maker Beats in 2014. This is also the largest known Apple acquisition since the company purchased Intel's smartphone modem business and patents for $1 billion in 2019. Q.ai...
Four iPhone 18 Pro Colors Mock Feature

iPhone 18 Pro and iPhone Ultra: Pre-Orders and Release Date

Thursday July 30, 2026 6:12 am PDT by
Apple has yet to reveal when the iPhone 18 Pro and iPhone Ultra will be announced and released, but the dates usually follow a familiar pattern. Labor Day is September 7 this year. The last time the holiday fell on that day was in 2020, but the iPhone event that year was delayed until October due to the COVID-19 pandemic. So, the last time Labor Day was on September 7 in a normal year was in ...

Top Rated Comments

18 weeks ago

This is going to be some serious cash flow incoming for Apple in this year.
I think this could be a major business for Apple - it’s way cheaper for a small business to buy a powerful Mac and run qwen 3.5 than pay for an enterprise license for a frontier model - and you don’t need to worry about privacy issues.
Score: 11 Votes (Like | Disagree)
18 weeks ago
On device is definitely gonna be the future.

I can’t help but wonder if Apple looked ahead and foresaw this when developing the M series, or if they’ve lucked into it.
Score: 10 Votes (Like | Disagree)
Justin Cymbal Avatar
18 weeks ago
M-Series chips at work😎
Score: 7 Votes (Like | Disagree)
18 weeks ago
As someone who downloads and experiments with everything possible…

There is a lot of delusion in this thread. Local language models below 100 billion parameters are quite useless. Even 100 billion parameters is considered the weak side. Fun to play with for a while but boredom and frustration sets in quickly.

So what happens is they want the next model…and then the next one…and then the next one…falsely believing their 16GB or 32GB machine will one day have the holy grail of small and powerful local language model.

But it doesn’t happen. The models keep growing and aside from being memory hungry the most important thing that makes them useable is memory bandwidth.

The top 5 language models in the world are all over a trillion parameters and what makes them useful and responsive is that they respond quickly and have GPU with over a terabyte of bandwidth.
Score: 6 Votes (Like | Disagree)
Kirkster Avatar
18 weeks ago
They are so far behind LM Studio. And only support for one model?
Score: 6 Votes (Like | Disagree)
18 weeks ago
This is going to be some serious cash flow incoming for Apple in this year.
Score: 6 Votes (Like | Disagree)

🔗 Related Apple News & Rumors

Stay updated with the latest Apple ecosystem news and verified rumors