Developer ports TurboFieldfare engine to DeepSeek-V4-Flash and Qwen 3.6
The TurboFieldfare engine now supports DeepSeek-V4-Flash 284B, running on 5.3GB of memory, and Qwen 3.6 35B, which runs on 1.4GB of RAM. The engine utilizes SSD streaming for MoE experts to reduce memory requirements.
2 sources
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