gemma-4-31B-it-INT8
INT8 quantization of google/gemma-4-31B-it, produced with llm-compressor.
Vision encoder, lm_head, embeddings, and norm layers are kept in original precision.
- Downloads last month
- 1,379
INT8 quantization of google/gemma-4-31B-it, produced with llm-compressor.
Vision encoder, lm_head, embeddings, and norm layers are kept in original precision.