TensorBlock

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

meraGPT/mera-mix-4x7B - GGUF

This repo contains GGUF format model files for meraGPT/mera-mix-4x7B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template


Model file specification

Filename Quant type File Size Description
mera-mix-4x7B-Q2_K.gguf Q2_K 8.236 GB smallest, significant quality loss - not recommended for most purposes
mera-mix-4x7B-Q3_K_S.gguf Q3_K_S 9.717 GB very small, high quality loss
mera-mix-4x7B-Q3_K_M.gguf Q3_K_M 10.785 GB very small, high quality loss
mera-mix-4x7B-Q3_K_L.gguf Q3_K_L 11.683 GB small, substantial quality loss
mera-mix-4x7B-Q4_0.gguf Q4_0 12.688 GB legacy; small, very high quality loss - prefer using Q3_K_M
mera-mix-4x7B-Q4_K_S.gguf Q4_K_S 12.799 GB small, greater quality loss
mera-mix-4x7B-Q4_K_M.gguf Q4_K_M 13.607 GB medium, balanced quality - recommended
mera-mix-4x7B-Q5_0.gguf Q5_0 15.485 GB legacy; medium, balanced quality - prefer using Q4_K_M
mera-mix-4x7B-Q5_K_S.gguf Q5_K_S 15.485 GB large, low quality loss - recommended
mera-mix-4x7B-Q5_K_M.gguf Q5_K_M 15.958 GB large, very low quality loss - recommended
mera-mix-4x7B-Q6_K.gguf Q6_K 18.456 GB very large, extremely low quality loss
mera-mix-4x7B-Q8_0.gguf Q8_0 23.904 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/mera-mix-4x7B-GGUF --include "mera-mix-4x7B-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/mera-mix-4x7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
40
GGUF
Model size
24.2B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/mera-mix-4x7B-GGUF

Quantized
(3)
this model

Evaluation results