Gemma 2 2B
A lightweight open-source large language model released by Google DeepMind, part of the Gemma 2 series with 2B parameters, suited to local deployment and resource-constrained scenarios.
Timeline (last 90 days)
Using convert_huggingface_to_gguf.py to convert Gemma 2 2B from safetensors to f16 GGUF took less than a minute in testing, and the output file is about 5.2GB.
Go Outside's default model is gemma-2-2b-it-q4f16_1-MLC-1k, which is the Gemma 2 2B instruction-tuned version with 4-bit quantization and a 1k context window.
All Facts (2)
Go Outside's default model is gemma-2-2b-it-q4f16_1-MLC-1k, which is the Gemma 2 2B instruction-tuned version with 4-bit quantization and a 1k context window.
50%UnverifiedUsing convert_huggingface_to_gguf.py to convert Gemma 2 2B from safetensors to f16 GGUF took less than a minute in testing, and the output file is about 5.2GB.
50%