Turbo-fieldfare engine runs Gemma 4 26B on Apple Silicon in 2 GB RAM
The Swift/Metal engine hits 5-6 tok/s on an 8 GB M2 MacBook Air and 31-35 tok/s on an M5 MacBook Pro, and includes an OpenAI-compatible local server.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Bezos, Arnault, Premji pour money into AI humanoid robot startups
- Claude agents return 19% vs S&P 500's 12% in $50K test
- Presenton launches 'OpenRouter for AI presentations' tool
- BenchSim launches AI judge video simulations for legal training
- Aavalynx Raises £1.5m Pre-Seed for Litigation Insights