Instructions to use webai-community/ai-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webai-community/ai-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="webai-community/ai-models",
	filename="CodeLlama-7b-Instruct-hf/gguf/codellama-7b-instruct.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use webai-community/ai-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf webai-community/ai-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf webai-community/ai-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf webai-community/ai-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf webai-community/ai-models: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 webai-community/ai-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf webai-community/ai-models: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 webai-community/ai-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf webai-community/ai-models:Q4_K_M

Use Docker

docker model run hf.co/webai-community/ai-models:Q4_K_M

LM Studio
Jan
Ollama
How to use webai-community/ai-models with Ollama:
```
ollama run hf.co/webai-community/ai-models:Q4_K_M
```

Unsloth Studio new

How to use webai-community/ai-models 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 webai-community/ai-models 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 webai-community/ai-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for webai-community/ai-models to start chatting

Docker Model Runner
How to use webai-community/ai-models with Docker Model Runner:
```
docker model run hf.co/webai-community/ai-models:Q4_K_M
```

Lemonade

How to use webai-community/ai-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull webai-community/ai-models:Q4_K_M

Run and chat with the model

lemonade run user.ai-models-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.

Download

Download a specific WebGPU model:

huggingface-cli download webai-community/ai-models --include "ai-models/<MODEL_NAME>/onnx-webgpu/*" --local-dir .

Download all WebGPU models:

huggingface-cli download webai-community/ai-models --include "*/onnx-webgpu/*" --local-dir .

Model List

model name	params size	gguf model	ort webgpu model	model info
Phi-4-mini-instruct	3.8B	gguf	onnx-webgpu	README
Phi-4-mini-reasoning	3.8B	gguf	onnx-webgpu	README
Phi-4-multimodal-instruct	6B		onnx-webgpu	README
Phi-3.5-mini-instruct	3.8B	gguf	onnx-webgpu	README
Phi-3-mini-4k-instruct	3.8B	gguf	onnx-webgpu	README
Phi-3-mini-128k-instruct	3.8B	gguf	onnx-webgpu	README
Qwen3-0.6B	0.6B	gguf	onnx-webgpu	README
Qwen3-1.7B	1.7B	gguf	onnx-webgpu	README
Qwen3-4B	4B	gguf	onnx-webgpu	README
Qwen3-8B	8B	gguf	onnx-webgpu	README
Qwen2.5-0.5B-Instruct	0.5B	gguf	onnx-webgpu	README
Qwen2.5-1.5B-Instruct	1.5B	gguf	onnx-webgpu	README
Qwen2.5-3B-Instruct	3B	gguf	onnx-webgpu	README
Qwen2.5-7B-Instruct	7B	gguf	onnx-webgpu	README
Qwen2-0.5B-Instruct	0.5B	gguf	onnx-webgpu	README
Qwen2-1.5B-Instruct	1.5B	gguf	onnx-webgpu	README
Qwen2-7B-Instruct	7B	gguf	onnx-webgpu	README
DeepSeek-R1-Distill-Qwen-1.5B	1.5B	gguf	onnx-webgpu	README
DeepSeek-R1-Distill-Qwen-7B	7B	gguf	onnx-webgpu	README
DeepSeek-R1-Distill-Llama-8B	8B	gguf	onnx-webgpu	README
DeepSeek-R1-0528-Qwen3-8B	8B	gguf	onnx-webgpu	README
gemma-3-1b-it	1B	gguf	onnx-webgpu	README
gemma-2-2b-it	2B	gguf	onnx-webgpu	README
gemma-2-9b-it	9B	gguf	onnx-webgpu	README
gemma-2b-it	2B	gguf	onnx-webgpu	README
gemma-7b-it	7B	gguf	onnx-webgpu	README
internlm2_5-7b-chat	7B	gguf	onnx-webgpu	README
internlm2-chat-1_8b	1.8B	gguf	onnx-webgpu	README
internlm2-chat-7b	7B	gguf	onnx-webgpu	README
Nemotron-Mini-4B-Instruct	4B	gguf	onnx-webgpu	README
Nemotron-Cascade-8B-Thinking	8B	gguf	onnx-webgpu	README
SmolLM2-1.7B-Instruct	1.7B	gguf	onnx-webgpu	README
SmolLM2-360M-Instruct	360M	gguf	onnx-webgpu	README
SmolLM2-135M-Instruct	135M	gguf	onnx-webgpu	README
SmolLM-1.7B-Instruct	1.7B	gguf	onnx-webgpu	README
SmolLM-360M-Instruct	360M	gguf	onnx-webgpu	README
SmolLM-135M-Instruct	135M	gguf	onnx-webgpu	README
Yi-Coder-1.5B-Chat	1.5B	gguf	onnx-webgpu	README
Qwen2.5-Coder-0.5B-Instruct	0.5B	gguf	onnx-webgpu	README
Qwen2.5-Coder-1.5B-Instruct	1.5B	gguf	onnx-webgpu	README
Qwen2.5-Coder-7B-Instruct	7B	gguf	onnx-webgpu	README
TinyLlama-1.1B-Chat-v1.0	1.1B	gguf	onnx-webgpu	README
CodeLlama-7b-Instruct-hf	7B	gguf	onnx-webgpu	README
SOLAR-10.7B-Instruct-v1.0	10.7B	gguf	onnx-webgpu	README
whisper-tiny	0.39B		onnx-webgpu	README
gpt-oss-20b	20B	gguf	onnx-webgpu	README
granite-3.1-2b-instruct	2B	gguf	onnx-webgpu	README
granite-3.1-8b-instruct	8B	gguf	onnx-webgpu	README
granite-3.2-2b-instruct	2B	gguf	onnx-webgpu	README
granite-3.2-8b-instruct	8B	gguf	onnx-webgpu	README
granite-3.3-2b-instruct	2B	gguf	onnx-webgpu	README
granite-3.3-8b-instruct	8B	gguf	onnx-webgpu	README
Ministral-8B-Instruct-2410	8B	gguf	onnx-webgpu	README
Mistral-7B-Instruct-v0.2	7B	gguf	onnx-webgpu	README
Mistral-7B-Instruct-v0.3	7B	gguf	onnx-webgpu	README
Mistral-Nemo-Instruct-2407	12B	gguf	onnx-webgpu	README
Yi-1.5-6B-Chat	6B	gguf	onnx-webgpu	README
Yi-1.5-9B-Chat	9B	gguf	onnx-webgpu	README

Downloads last month: 492

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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