--- language: - en library_name: transformers license: apache-2.0 tags: - unsloth - transformers - gemma - gemma-7b - TensorBlock - GGUF base_model: unsloth/gemma-7b-it ---
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

## unsloth/gemma-7b-it - GGUF This repo contains GGUF format model files for [unsloth/gemma-7b-it](https://huggingface.co/unsloth/gemma-7b-it). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
Run them on the TensorBlock client using your local machine ↗
## Prompt template ``` user {prompt} model ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [gemma-7b-it-Q2_K.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q2_K.gguf) | Q2_K | 3.242 GB | smallest, significant quality loss - not recommended for most purposes | | [gemma-7b-it-Q3_K_S.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q3_K_S.gguf) | Q3_K_S | 3.709 GB | very small, high quality loss | | [gemma-7b-it-Q3_K_M.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q3_K_M.gguf) | Q3_K_M | 4.069 GB | very small, high quality loss | | [gemma-7b-it-Q3_K_L.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q3_K_L.gguf) | Q3_K_L | 4.386 GB | small, substantial quality loss | | [gemma-7b-it-Q4_0.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q4_0.gguf) | Q4_0 | 4.668 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [gemma-7b-it-Q4_K_S.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q4_K_S.gguf) | Q4_K_S | 4.700 GB | small, greater quality loss | | [gemma-7b-it-Q4_K_M.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q4_K_M.gguf) | Q4_K_M | 4.964 GB | medium, balanced quality - recommended | | [gemma-7b-it-Q5_0.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q5_0.gguf) | Q5_0 | 5.570 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [gemma-7b-it-Q5_K_S.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q5_K_S.gguf) | Q5_K_S | 5.570 GB | large, low quality loss - recommended | | [gemma-7b-it-Q5_K_M.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q5_K_M.gguf) | Q5_K_M | 5.723 GB | large, very low quality loss - recommended | | [gemma-7b-it-Q6_K.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q6_K.gguf) | Q6_K | 6.529 GB | very large, extremely low quality loss | | [gemma-7b-it-Q8_0.gguf](https://huggingface.co/tensorblock/gemma-7b-it-GGUF/blob/main/gemma-7b-it-Q8_0.gguf) | Q8_0 | 8.454 GB | very large, extremely low quality loss - not recommended | ## Downloading instruction ### Command line Firstly, install Huggingface Client ```shell pip install -U "huggingface_hub[cli]" ``` Then, downoad the individual model file the a local directory ```shell huggingface-cli download tensorblock/gemma-7b-it-GGUF --include "gemma-7b-it-Q2_K.gguf" --local-dir MY_LOCAL_DIR ``` If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try: ```shell huggingface-cli download tensorblock/gemma-7b-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```