TurboFieldfare
4 likes
Custom Mac runtime allows instruction-tuned 26-billion-parameter model inference in about 2 GB RAM by streaming only required model experts from SSD, with 1.35 GB core and cache in memory. Supports 8 GB Apple Silicon Macs with CLI and native app, measured in 103 scenarios.
Platforms
- Mac
Features
Highlights All activities
TurboFieldfare News & Activities
Recent activities
c17s5qhu added TurboFieldfare as alternative to oxproxion
Paul added TurboFieldfare as alternative to Ollaya- Ben liked TurboFieldfare
This is a really clever idea. It's impressive to see such a large model running on an 8 GB Mac without needing high-end hardware. I probably wouldn't use it every day, but I always enjoy projects that find creative ways to make AI more accessible.
- Viktor Korobov liked TurboFieldfare
- Wierzciu liked TurboFieldfare
- Shahid Adnan wali liked TurboFieldfare
- Mauricio B. Holguin updated TurboFieldfare
- Paul added Large Language Model (LLM) as a feature to TurboFieldfare
Paul added TurboFieldfare as alternative to Locally AI, Apollo AI, SmolChat, GPTMobile and 11 more
Developed by
Andrey Mikhaylov Licensing
Open Source (Apache-2.0) and Free product.Written in
Alternatives
17 alternatives listedBadge
Get an embeddable badge for TurboFieldfareSupported Languages
AlternativeTo Categories
AI Tools & Services, OS & Utilities, System & HardwareGitHub repository
- 7,079 Stars
- 458 Forks
- 53 Open Issues
- Updated
Comments and Reviews
This is a really clever idea. It's impressive to see such a large model running on an 8 GB Mac without needing high-end hardware. I probably wouldn't use it every day, but I always enjoy projects that find creative ways to make AI more accessible.