tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF

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

mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16 - GGUF

This repo contains GGUF format model files for mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16.

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

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q2_K.gguf	Q2_K	26.375 GB	smallest, significant quality loss - not recommended for most purposes
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_S.gguf	Q3_K_S	30.912 GB	very small, high quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_M.gguf	Q3_K_M	34.267 GB	very small, high quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_L.gguf	Q3_K_L	37.141 GB	small, substantial quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_0.gguf	Q4_0	39.970 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_S.gguf	Q4_K_S	40.347 GB	small, greater quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_M.gguf	Q4_K_M	42.520 GB	medium, balanced quality - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_0.gguf	Q5_0	48.657 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_S.gguf	Q5_K_S	48.657 GB	large, low quality loss - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_M.gguf	Q5_K_M	49.950 GB	large, very low quality loss - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K	Q6_K	57.888 GB	very large, extremely low quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0	Q8_0	74.975 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/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF --include "Llama-3.1-Nemotron-70B-Instruct-HF-bf16-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/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'