internlm2-chat-1_8b-4bit

4-bit affine quantization of internlm/internlm2-chat-1_8b, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).

Conversion

ffai convert internlm/internlm2-chat-1_8b --bits 4 \
    --upload-repo ekryski/internlm2-chat-1_8b-4bit

See also

• FFAI — fast Apple Silicon LLM inference. Model.load("ekryski/internlm2-chat-1_8b-4bit") runs this checkpoint end-to-end.
• FFAI quickstart
• FFAI quantization docs