LLM Central Library

The models described below are available for all VACC users at the LLM Central Library, located at /gpfs1/llm.

To request a new model be added to the library, see Requesting a New Model.

Llama, from Meta

Meta's Llama (version 2, 3, 4, and code-llama) in multiple formats (Meta original format, HuggingFace safetensors, and GGUF)

• Meta's main Llama page
• Llama on HuggingFace

For Llama-4 there is a code repository available that provides guidance and scripts for setting up and running the model on the VACC; see the VACC Tools UVM GitLab group

/gpfs1/llm/
├── code-llama
│   └── CodeLlama-7b-hf
├── llama-2
│   ├── llama-2-13b
│   ├── llama-2-13b-chat
│   ├── llama-2-70b
│   ├── llama-2-70b-chat
│   ├── llama-2-7b
│   ├── llama-2-7b-chat
├── llama-2-gguf
│   ├── llama-2-13b
│   ├── llama-2-70b
│   └── llama-2-7b
├── llama-2-hf
│   ├── llama-2-13b
│   ├── llama-2-13b-chat
│   ├── llama-2-70b
│   ├── llama-2-70b-chat
│   ├── llama-2-7b
│   ├── llama-2-7b-chat
├── llama-3
│   ├── Meta-Llama-3-70B
│   ├── Meta-Llama-3-70B-Instruct
│   ├── Meta-Llama-3-8B
│   ├── Meta-Llama-3-8B-Instruct
├── llama-3.1
│   ├── Meta-Llama-3.1-405B-Instruct-MP16
│   ├── Meta-Llama-3.1-405B-MP16
│   ├── Meta-Llama-3.1-70B
│   ├── Meta-Llama-3.1-70B-Instruct
│   ├── Meta-Llama-3.1-8B
│   ├── Meta-Llama-3.1-8B-Instruct
│   ├── Meta-Llama-Guard-3-8B
│   ├── Meta-Llama-Guard-3-8B-INT8-HF
│   └── Prompt-Guard
├── llama-3.1-hf
│   └── Meta-Llama-3.1-8B-Instruct
├── llama-3.2-hf
│   └── Meta-Llama-3.2-3B-Instruct
├── llama-3.3
│   └── Meta-Llama-3.3-70B-Instruct
├── llama-3.3-hf
│   └── Meta-Llama-3.3-70B-Instruct
├── llama-3-gguf
│   ├── Meta-Llama-3-70B
│   ├── Meta-Llama-3-70B-Instruct
│   ├── Meta-Llama-3-8B
│   └── Meta-Llama-3-8B-Instruct
├── llama-3-hf
│   ├── Meta-Llama-3-70B
│   ├── Meta-Llama-3-70B-Instruct
│   ├── Meta-Llama-3-8B
│   └── Meta-Llama-3-8B-Instruct
├── llama-4.0
│   ├── Llama-4-Maverick-17B-128E
│   ├── Llama-4-Maverick-17B-128E-Instruct
│   ├── Llama-4-Maverick-17B-128E-Instruct-fp8
│   ├── Llama-4-Scout-17B-16E
│   ├── Llama-4-Scout-17B-16E-Instruct
├── llama-4.0-gguf
│   ├── Llama-4-Maverick-17B-128E-Instruct
│   └── Llama-4-Scout-17B-16E-Instruct
└── llama-4.0-hf
    ├── Llama-4-Maverick-17B-128E
    ├── Llama-4-Maverick-17B-128E-Instruct
    ├── Llama-4-Maverick-17B-128E-Instruct-FP8
    ├── Llama-4-Scout-17B-16E
    └── Llama-4-Scout-17B-16E-Instruct

Arctic Embed, from Snowflake

The safetensor-format version of Snowflake's Arctic text-embedding model is installed to:

/gpfs1/llm/
└── snowflake-arctic-embed-l