What it does
Run Gemma locally through a Mac app, CLI, or loopback chat server.
Read the sourceReviewed
turbo-fieldfare
Open-source engine running Gemma 4 26B in 2 GB RAM on Apple Silicon Macs.
Why it made the shelf
This is an open-source inference engine designed to run large language models efficiently on specific hardware, which is.
On 6 boards
- First seen
- 2 months ago
- Best score
- 916 points · 345 comments
From official documentation
Product details
Know before you choose
Requires Apple Silicon, macOS 26 and Metal 4. Image support needs an M2 or newer Mac and an extra model pack.
Read the sourceReviewed
Know before you choose
Audio and video are unsupported. The app and CLI do not execute tools; server tool calls must be handled by the client.
Read the sourceReviewed
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review current
Public trail
Where it showed up
20 references from 8 publishers.
- First trace
- Hacker News13 months ago
- Strongest thread
- Hacker News345 comments
- 01Hacker NewsStrongest discussion
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
- 02
