llmbd.info

bartowski/Llama-3.2-3B-Instruct-GGUF

See on Huggingface



What do people say...

spotbot2k
  • Would recommend? yes!
  • Quantization Q8_0
Runs at reasonable speed on a smartphone (llama.cpp on **CPU**). Not like it's ready for production but enough for translation or minimal chit chat.

Post a Review