LM/Gemma 4

Experiment

# search
hf models ls --search "gemma-4" --apps llama.cpp --expand "downloads,likes,lastModified" --sort downloads --no-truncate --limit 10

# unsloth
hf models ls --tree -R -h unsloth/gemma-4-E4B-it-qat-GGUF
hf models ls --tree -R -h unsloth/gemma-4-12B-it-qat-GGUF

hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "*UD-Q4_K_XL*" --include "*mmproj-BF16*"

find ~/.cache/huggingface/hub -name "*gemma-4-E4B-it-qat-GGUF"

tree -h ~/.cache/huggingface/hub/models--unsloth--gemma-4-E4B-it-qat-GGUF