mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-30 18:19:33 -04:00
Offer intermediate quantizations alongside the existing Q4 and Q8 builds. Keep the shared BF16 projector and llama.cpp MTP configuration. Pin new files to a Hugging Face revision and document explicit variant selection. Assisted-by: Codex:gpt-6