Mike Basios

mike18

turintech

·

http://www.turintech.ai

AI & ML interests

Co-founder & CTO at TurinTech AI. We build Artemis, which optimises code and models to run well on any device.

Recent Activity

updated a collection 1 day ago

Compressed LLMs

updated a collection 1 day ago

Compressed LLMs

updated a collection 1 day ago

Compressed LLMs

View all activity

Organizations

New activity in turintech/README 26 days ago

Feedback and requests: which model should we shrink next?

#1 opened 26 days ago by

New activity in jaredpalmer/kev-9b 26 days ago

Smaller GGUF for stock llama.cpp (4.8 GB, fits a 12 GB GPU)

#3 opened 26 days ago by

New activity in jaredpalmer/kev-4b 26 days ago

Smaller GGUF for stock llama.cpp (2.5 GB)

#3 opened 26 days ago by

New activity in Cloudflare/clef-flash 26 days ago

Smaller GGUF for stock llama.cpp (4.9 GB)

#6 opened 26 days ago by

New activity in Cloudflare/clef 26 days ago

Smaller GGUF for stock llama.cpp, fits a 16 GB GPU for text

#11 opened 26 days ago by

New activity in perplexity-ai/pplx-decider-v1.1-27b 26 days ago

Smaller GGUF that runs on stock llama.cpp (/v1/systemone)

#4 opened 26 days ago by