deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF

fix: re-upload gemma4-e4b-opus-f16.gguf with properly de-quantized embeddings

fix: re-upload gemma4-e4b-opus-Q8_0.gguf with properly de-quantized embeddings

fix: re-upload gemma4-e4b-opus-Q5_K_M.gguf with properly de-quantized embeddings

fix: re-upload gemma4-e4b-opus-Q4_K_M.gguf with properly de-quantized embeddings

add gemma4-e4b-opus-f16.gguf

add gemma4-e4b-opus-Q8_0.gguf

add gemma4-e4b-opus-Q5_K_M.gguf

add gemma4-e4b-opus-Q4_K_M.gguf

update model card with actual GGUF file sizes

add GGUF conversion script

initial model card for GGUF version

initial commit