AllYouCanTech

# Local AI Models Now Operate More Swiftly on Ollama on Apple Silicon Macs

If you’re unfamiliar with [Ollama](https://ollama.com/), it is an application available for Mac, Linux, and Windows that enables users to execute AI models locally on their systems. Unlike cloud-based applications like ChatGPT, which do not function locally and necessitate an internet connection, Ollama permits users to load and operate models directly on their devices. These models may be obtained from open-source platforms such as Hugging Face, or even straight from the model provider.

Nonetheless, executing a large language model (LLM) locally can pose significant difficulties, since even smaller, lightweight LLMs typically require considerable amounts of RAM and GPU memory. To mitigate this problem, Ollama has unveiled a preview version (Ollama 0.19) of its application, now constructed upon Apple’s machine learning framework, MLX, leveraging its unified memory architecture to ensure local AI models run at increased speeds on Apple silicon Macs.

This leads to a notable acceleration of Ollama on all Apple Silicon devices. Utilizing Apple’s M5, M5 Pro, and M5 Max chips, Ollama takes advantage of the new GPU Neural Accelerators to improve both time to first token (TTFT) and generation rate (tokens per second). With this upgrade, Ollama asserts it is now swifter to execute personal assistants like OpenClaw, as well as coding agents such as Claude Code, OpenCode, or Codex.

The stipulation is that Ollama advises users to confirm they possess a Mac with over 32GB of unified memory, which may not be the circumstance for many individuals eager to run LLMs locally.

To discover more about Ollama, [click this link](https://ollama.com/). For additional information about Apple’s MLX project, all the details can be found [here](https://opensource.apple.com/projects/mlx/).

### Apple Introduces Firmware Update for AirTag 2

Alongside the debut of the new AirPods Max 2, Apple has also introduced a firmware update for the AirTag 2, which was made available earlier this year. This update, designated as firmware version 3.0.45, supersedes the previous version 3.0.41 that accompanied the device.

#### How to Verify Your Firmware Version

To see if your AirTag 2 is up-to-date with the latest firmware, perform the following steps:

1. Open the Find My app on your device.
2. Tap the Items tab.
3. Choose your AirTag from the list.
4. Tap on the name of your AirTag to check its serial number and firmware version.

It’s crucial to understand that Apple does not currently offer a method for users to manually install firmware updates, indicating that the update will be deployed automatically.

#### Anticipated Enhancements

Although Apple has not provided detailed release notes for this firmware update, it’s expected that the update resolves bugs identified post the AirTag 2’s launch and incorporates performance improvements. The AirTag 2 was built with enhanced features, including a second-generation Ultra Wideband chip that expands tracking range and speakers that are 50% louder than its predecessor.

Furthermore, the AirTag 2 features sophisticated security measures designed to prevent unauthorized tracking. These features include cross-platform alerts and distinctive Bluetooth identifiers that change regularly, ensuring the privacy of users.

#### Cost and Availability

The AirTag 2 is available for $29 for an individual unit or $99 for a pack of four. With its upgraded capabilities and security features, it continues to be a favored option for users aiming to monitor their possessions.

For those looking to buy, the AirTag 2 can be found on Amazon and various other retailers.