Open Source · Hacker News ·

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

TurboFieldfare is an open-source Swift and Metal inference engine that runs 4-bit Gemma 4 26B on M-series Macs using about 2 GB of RAM by streaming model experts from SSD. Reported speeds range from 5–6 tokens/s on an 8 GB M2 MacBook Air to 31–35 tokens/s on an M5 MacBook Pro.

Read the full story at Hacker News →