Gemma-2-7B-Instruct

A 7B parameter instruction-tuned model from Google with an Apache 2.0 licence; uses approximately 6GB RAM in 4-bit GGUF format and is noted for strong reasoning capability on M2 hardware.

Details

• Services: text generation, instruction following, reasoning

Related

gguf-4-bit-quantisation local-llm-inference llama-cpp ollama mac-mini-m2