Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
MediaTek-Research/Breeze-7B-Instruct-v1_0 - GGUF
This repo contains GGUF format model files for MediaTek-Research/Breeze-7B-Instruct-v1_0.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<s> {system_prompt} [INST] {prompt} [/INST]
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Breeze-7B-Instruct-v1_0-Q2_K.gguf | Q2_K | 2.664 GB | smallest, significant quality loss - not recommended for most purposes |
| Breeze-7B-Instruct-v1_0-Q3_K_S.gguf | Q3_K_S | 3.091 GB | very small, high quality loss |
| Breeze-7B-Instruct-v1_0-Q3_K_M.gguf | Q3_K_M | 3.421 GB | very small, high quality loss |
| Breeze-7B-Instruct-v1_0-Q3_K_L.gguf | Q3_K_L | 3.703 GB | small, substantial quality loss |
| Breeze-7B-Instruct-v1_0-Q4_0.gguf | Q4_0 | 3.985 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Breeze-7B-Instruct-v1_0-Q4_K_S.gguf | Q4_K_S | 4.015 GB | small, greater quality loss |
| Breeze-7B-Instruct-v1_0-Q4_K_M.gguf | Q4_K_M | 4.227 GB | medium, balanced quality - recommended |
| Breeze-7B-Instruct-v1_0-Q5_0.gguf | Q5_0 | 4.827 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Breeze-7B-Instruct-v1_0-Q5_K_S.gguf | Q5_K_S | 4.827 GB | large, low quality loss - recommended |
| Breeze-7B-Instruct-v1_0-Q5_K_M.gguf | Q5_K_M | 4.952 GB | large, very low quality loss - recommended |
| Breeze-7B-Instruct-v1_0-Q6_K.gguf | Q6_K | 5.722 GB | very large, extremely low quality loss |
| Breeze-7B-Instruct-v1_0-Q8_0.gguf | Q8_0 | 7.411 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Breeze-7B-Instruct-v1_0-GGUF --include "Breeze-7B-Instruct-v1_0-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:
huggingface-cli download tensorblock/Breeze-7B-Instruct-v1_0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 0
Model tree for tensorblock/Breeze-7B-Instruct-v1_0-GGUF
Base model
MediaTek-Research/Breeze-7B-Instruct-v1_0