Tamas05/gemma-3-27b-it-8bit

Gemma 3-27B IT (8-bit)

This is an 8-bit quantized version of the google/gemma-3-27b-it model.

This is the 8-bit quantized version of the https://huggingface.co/google/gemma-3-27b-it model. The Zip-File contains the tokenizer and the model in the following structure:

  total 27G
  -rw-r--r-- 1 root root   35 Mar 26 17:15 added_tokens.json
  -rw-r--r-- 1 root root 2.1K Mar 26 17:11 config.json
  -rw-r--r-- 1 root root  215 Mar 26 17:11 generation_config.json
  -rw-r--r-- 1 root root 4.7G Mar 26 17:12 model-00001-of-00006.safetensors
  -rw-r--r-- 1 root root 4.7G Mar 26 17:12 model-00002-of-00006.safetensors
  -rw-r--r-- 1 root root 4.7G Mar 26 17:13 model-00003-of-00006.safetensors
  -rw-r--r-- 1 root root 4.7G Mar 26 17:14 model-00004-of-00006.safetensors
  -rw-r--r-- 1 root root 4.7G Mar 26 17:14 model-00005-of-00006.safetensors
  -rw-r--r-- 1 root root 3.8G Mar 26 17:15 model-00006-of-00006.safetensors
  -rw-r--r-- 1 root root 242K Mar 26 17:15 model.safetensors.index.json
  -rw-r--r-- 1 root root  662 Mar 26 17:15 special_tokens_map.json
  -rw-r--r-- 1 root root 1.2M Mar 26 17:15 tokenizer_config.json
  -rw-r--r-- 1 root root  32M Mar 26 17:15 tokenizer.json
  -rw-r--r-- 1 root root 4.5M Mar 26 17:15 tokenizer.model