|
--- |
|
license: gemma |
|
base_model: |
|
- google/gemma-3-27b-it |
|
tags: |
|
- gemma |
|
- google |
|
- instruct |
|
- llm |
|
- gguf |
|
- GGUF |
|
--- |
|
|
|
# Quant Infos |
|
|
|
- Requires llama.cpp [b4875](https://github.com/ggml-org/llama.cpp/releases/tag/b4875) |
|
- LLM ONLY (No vision support) |
|
- quants done with an importance matrix for improved quantization loss |
|
- Quantized ggufs & imatrix from hf bf16, through bf16. `safetensors bf16 -> gguf bf16 -> quant` for *optimal* quant loss. |
|
- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S (WIP) |
|
- Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski). |
|
``` |
|
./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix |
|
``` |
