Ollama
Runs open models such as gpt-oss, Qwen and DeepSeek on your own computer.
Open the source (opens github.com) https://github.com/ollama/ollama
Before you use it
- Big models need a lot of memory. The install command runs a script from the internet.
What it is
Models from Ollama. Good for:
- Work with private data without sending it to a cloud API
- Experiment with open models for free
Level: beginner
How to get it
Linux install
curl -fsSL https://ollama.com/install.sh | sh
Copied from the official README or docs
Related
-
llama.cpp
ModelsThe C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.
-
Whisper
ModelsOpenAI's open speech-to-text model.
pip install -U openai-whisper -
Hugging Face Hub
ModelsThe main public hub for open models, datasets and demo apps (Spaces).
-
stable-audio-open-1.0
Modelstext to audio model by stabilityai · stable-audio-tools
stabilityai/stable-audio-open-1.0 -
oasis-500m
Modelsmodel by Etched · open-oasis
Etched/oasis-500m -
Qwen3.8-Flash-Next-FP4-Local
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/Qwen3.8-Flash-Next-FP4-Local