TensorBlock

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

Technoculture/Mediquad-4x7b - GGUF

This repo contains GGUF format model files for Technoculture/Mediquad-4x7b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template


Model file specification

Filename Quant type File Size Description
Mediquad-4x7b-Q2_K.gguf Q2_K 7.235 GB smallest, significant quality loss - not recommended for most purposes
Mediquad-4x7b-Q3_K_S.gguf Q3_K_S 8.530 GB very small, high quality loss
Mediquad-4x7b-Q3_K_M.gguf Q3_K_M 9.489 GB very small, high quality loss
Mediquad-4x7b-Q3_K_L.gguf Q3_K_L 10.295 GB small, substantial quality loss
Mediquad-4x7b-Q4_0.gguf Q4_0 11.132 GB legacy; small, very high quality loss - prefer using Q3_K_M
Mediquad-4x7b-Q4_K_S.gguf Q4_K_S 11.231 GB small, greater quality loss
Mediquad-4x7b-Q4_K_M.gguf Q4_K_M 11.945 GB medium, balanced quality - recommended
Mediquad-4x7b-Q5_0.gguf Q5_0 13.581 GB legacy; medium, balanced quality - prefer using Q4_K_M
Mediquad-4x7b-Q5_K_S.gguf Q5_K_S 13.581 GB large, low quality loss - recommended
Mediquad-4x7b-Q5_K_M.gguf Q5_K_M 14.000 GB large, very low quality loss - recommended
Mediquad-4x7b-Q6_K.gguf Q6_K 16.184 GB very large, extremely low quality loss
Mediquad-4x7b-Q8_0.gguf Q8_0 20.960 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/Mediquad-4x7b-GGUF --include "Mediquad-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/Mediquad-4x7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
111
GGUF
Model size
19.7B 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/Mediquad-4x7b-GGUF

Quantized
(1)
this model