DictaLM 3.0 1.7B Instruct — GGUF Q8_0

8-bit GGUF conversion of dicta-il/DictaLM-3.0-1.7B-Instruct for llama.cpp (Metal), used by the LearnBySpeaking macOS app.

Converted with llama.cpp convert_hf_to_gguf.py --outtype q8_0 from the official weights. Chat template: the official one, embedded.

llama-server -m dictalm-1.7b-instruct-q8_0.gguf --jinja -ngl 99

SHA-256: 871d3ba72c76a5fa25a1915be001d412e817191d6f32f817bf67fb6c7266c8a7

License: Apache-2.0, same as the original model by Dicta.