InnerVault

Ollama

Hand-checked InnerVault (hand-checked), 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

  1. llama.cpp

    Models

    The C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.

    Hand-checked InnerVault (hand-checked), ggml-org MIT

  2. Whisper

    Models

    OpenAI's open speech-to-text model.

    Hand-checked InnerVault (hand-checked), OpenAI MIT

    pip install -U openai-whisper
  3. The main public hub for open models, datasets and demo apps (Spaces).

    Hand-checked InnerVault (hand-checked), Hugging Face Each model has its own licence

  4. text to audio model by stabilityai · stable-audio-tools

    Indexed Hugging Face Hub, stabilityai 1,986 ♥otherUpdated 17 months ago 1 note

    stabilityai/stable-audio-open-1.0
  5. oasis-500m

    Models

    model by Etched · open-oasis

    Stale Hugging Face Hub, Etched 510 ♥mitUpdated 2 years ago 1 note

    Etched/oasis-500m
  6. image text to text model by nvidia · Model Optimizer

    Indexed Hugging Face Hub, nvidia 409 ♥otherUpdated 32 days ago

    nvidia/Qwen3.8-Flash-Next-FP4-Local