Instructions to use vikramlingam/Ensemble-AI-Vault with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vikramlingam/Ensemble-AI-Vault with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vikramlingam/Ensemble-AI-Vault",
	filename="weights/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use vikramlingam/Ensemble-AI-Vault with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vikramlingam/Ensemble-AI-Vault:Q4_K_M

Use Docker

docker model run hf.co/vikramlingam/Ensemble-AI-Vault:Q4_K_M

LM Studio
Jan
Ollama
How to use vikramlingam/Ensemble-AI-Vault with Ollama:
```
ollama run hf.co/vikramlingam/Ensemble-AI-Vault:Q4_K_M
```

Unsloth Studio new

How to use vikramlingam/Ensemble-AI-Vault with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vikramlingam/Ensemble-AI-Vault to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vikramlingam/Ensemble-AI-Vault to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vikramlingam/Ensemble-AI-Vault to start chatting

Docker Model Runner
How to use vikramlingam/Ensemble-AI-Vault with Docker Model Runner:
```
docker model run hf.co/vikramlingam/Ensemble-AI-Vault:Q4_K_M
```

Lemonade

How to use vikramlingam/Ensemble-AI-Vault with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vikramlingam/Ensemble-AI-Vault:Q4_K_M

Run and chat with the model

lemonade run user.Ensemble-AI-Vault-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Ensemble AI Model Vault

This repository is a personal, private collection of various open-source Large Language Models (LLMs) and Vision-Language Models (VLMs).

Disclaimer & Attribution

This repository is strictly for personal use and developer experimentation.
All models contained herein are the property of their respective creators (Meta, Google, Alibaba/Qwen, IBM, Microsoft, Liquid AI, etc.).
Direct attribution and original source links can be found in the /licenses folder and the model catalog below.
This collection is provided "as-is" without any warranties. The owner of this repository does not claim ownership of the model weights.

Model Manifest (March 2026)

Model	Quantization	Source Type
Qwen 3.5 (0.8B, 2B, 4B)	Q4_K_M	SLM / General
Qwen 3.5 VL (0.8B, 4B)	Q4_K_M	VLM / Multimodal
IBM Granite 3.1 2B	Q4_K_M	Enterprise
Liquid AI LFM 2.5	Q4_K_M	Linear-Time
DeepSeek R1 Distill	Q4_K_M	Reasoning
Gemma 3 Vision	Q4_K_M	Multimodal
Phi-4 Mini	Q4_K_M	Logic
Sarvam 2B	Q4_K_M	Indic

Licensing

Individual licenses for each model are located in the /licenses directory. By using these models, you agree to abide by the terms set forth by the original authors.

Downloads last month: 176

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support