tensorblock/speechless-codellama-34b-v1.9-GGUF

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

uukuguy/speechless-codellama-34b-v1.9 - GGUF

This repo contains GGUF format model files for uukuguy/speechless-codellama-34b-v1.9.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

Model file specification

Filename	Quant type	File Size	Description
speechless-codellama-34b-v1.9-Q2_K.gguf	Q2_K	12.506 GB	smallest, significant quality loss - not recommended for most purposes
speechless-codellama-34b-v1.9-Q3_K_S.gguf	Q3_K_S	14.605 GB	very small, high quality loss
speechless-codellama-34b-v1.9-Q3_K_M.gguf	Q3_K_M	16.306 GB	very small, high quality loss
speechless-codellama-34b-v1.9-Q3_K_L.gguf	Q3_K_L	17.772 GB	small, substantial quality loss
speechless-codellama-34b-v1.9-Q4_0.gguf	Q4_0	19.052 GB	legacy; small, very high quality loss - prefer using Q3_K_M
speechless-codellama-34b-v1.9-Q4_K_S.gguf	Q4_K_S	19.192 GB	small, greater quality loss
speechless-codellama-34b-v1.9-Q4_K_M.gguf	Q4_K_M	20.220 GB	medium, balanced quality - recommended
speechless-codellama-34b-v1.9-Q5_0.gguf	Q5_0	23.237 GB	legacy; medium, balanced quality - prefer using Q4_K_M
speechless-codellama-34b-v1.9-Q5_K_S.gguf	Q5_K_S	23.237 GB	large, low quality loss - recommended
speechless-codellama-34b-v1.9-Q5_K_M.gguf	Q5_K_M	23.839 GB	large, very low quality loss - recommended
speechless-codellama-34b-v1.9-Q6_K.gguf	Q6_K	27.684 GB	very large, extremely low quality loss
speechless-codellama-34b-v1.9-Q8_0.gguf	Q8_0	35.856 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/speechless-codellama-34b-v1.9-GGUF --include "speechless-codellama-34b-v1.9-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/speechless-codellama-34b-v1.9-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'