Feedback and requests: which model should we shrink next?

#1
by mike18 - opened

We've released smaller GGUF builds of Clef, Clef-Flash, Perplexity's Decider and Kev for stock llama.cpp, plus Gemma 4 E4B and E2B. Each file is checked against its original, with the full comparisons on its card.

Tell us here:

  • which model you'd like smaller next, and on what hardware you'd run it
  • anything that doesn't match what the cards say
  • what you're using the decision models for

Decision models: https://huggingface.co/collections/turintech/artemis-edge-decision-models-6accea74eb7016a886f25fdb
Compressed LLMs: https://huggingface.co/collections/turintech/artemis-edge-compressed-llms-6acd251457ba2b9f33ad9d8a

mike18 pinned discussion

Sign up or log in to comment