OpenLLM Buddy

Open-source AI models on dedicated GPU

The same OpenLLM catalog as the GPU templates on Self Deploy. Each AI model is paired with a dedicated GPU and flat time packs, with an OpenAI-compatible API on your instance.

Catalog

8 AI models

  • Kimi-K3-Uncensored-GGUF maker logoKimi-K3-Uncensored-GGUF

    Deployed on dedicated GPU

    8× H100 80GB

    AI model + GPU instance

    Kimi-K3-Uncensored-GGUF is in the OpenLLM catalog on a dedicated 8× H100 80GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    8× H100 80GB
    GPUs
    8
    Memory
    80GB
    View AI model
  • Qwen-Image-2.1-Uncensored-GGUF maker logoQwen-Image-2.1-Uncensored-GGUF

    Deployed on dedicated GPU

    RTX 4090 24GB

    AI model + GPU instance

    Qwen-Image-2.1-Uncensored-GGUF is in the OpenLLM catalog on a dedicated RTX 4090 24GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    RTX 4090 24GB
    GPUs
    1
    Memory
    24GB
    View AI model
  • LTX-2.5-uncensored-v1.1-FP8 maker logoLTX-2.5-uncensored-v1.1-FP8

    Deployed on dedicated GPU

    RTX 5090 32GB

    AI model + GPU instance

    LTX-2.5-uncensored-v1.1-FP8 is in the OpenLLM catalog on a dedicated RTX 5090 32GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    RTX 5090 32GB
    GPUs
    1
    Memory
    32GB
    View AI model
  • gemma-4-31B-it-uncensored maker logogemma-4-31B-it-uncensored

    Deployed on dedicated GPU

    RTX 4090 24GB

    AI model + GPU instance

    gemma-4-31B-it-uncensored is in the OpenLLM catalog on a dedicated RTX 4090 24GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    RTX 4090 24GB
    GPUs
    1
    Memory
    24GB
    View AI model
  • GLM-5.3-Flash-Uncensored-FP8 maker logoGLM-5.3-Flash-Uncensored-FP8

    Deployed on dedicated GPU

    4× H200 141GB

    AI model + GPU instance

    GLM-5.3-Flash-Uncensored-FP8 is in the OpenLLM catalog on a dedicated 4× H200 141GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    4× H200 141GB
    GPUs
    4
    Memory
    141GB
    View AI model
  • MiMo-V2.6-Pro-RL-UNCENSORED maker logoMiMo-V2.6-Pro-RL-UNCENSORED

    Deployed on dedicated GPU

    8× H200

    AI model + GPU instance

    MiMo-V2.6-Pro-RL-UNCENSORED is in the OpenLLM catalog on a dedicated 8× H200. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    8× H200
    GPUs
    8
    Memory
    141GB
    View AI model
  • Qwen3.8-27B-Uncensored-FP8 maker logoQwen3.8-27B-Uncensored-FP8

    Deployed on dedicated GPU

    H100 80GB

    AI model + GPU instance

    Qwen3.8-27B-Uncensored-FP8 is in the OpenLLM catalog on a dedicated H100 80GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    H100 80GB
    GPUs
    1
    Memory
    80GB
    View AI model
  • DeepSeek-V4.1-Flash-UNCENSORED-FP8 maker logoDeepSeek-V4.1-Flash-UNCENSORED-FP8

    Deployed on dedicated GPU

    4× H200 141GB

    AI model + GPU instance

    DeepSeek-V4.1-Flash-UNCENSORED-FP8 is in the OpenLLM catalog on a dedicated 4× H200 141GB. Deploy it with a flat time pack and call your instance through an OpenAI-compatible API.

    GPU
    4× H200 141GB
    GPUs
    4
    Memory
    141GB
    View AI model