Instructions to use OpenBloom/runtime-releases with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use OpenBloom/runtime-releases with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf OpenBloom/runtime-releases:Q4_K_M # Run inference directly in the terminal: llama cli -hf OpenBloom/runtime-releases:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf OpenBloom/runtime-releases:Q4_K_M # Run inference directly in the terminal: llama cli -hf OpenBloom/runtime-releases:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf OpenBloom/runtime-releases:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf OpenBloom/runtime-releases:Q4_K_M
Use Docker
docker model run hf.co/OpenBloom/runtime-releases:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use OpenBloom/runtime-releases with Ollama:
ollama run hf.co/OpenBloom/runtime-releases:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use OpenBloom/runtime-releases with Docker Model Runner:
docker model run hf.co/OpenBloom/runtime-releases:Q4_K_M
- Lemonade
How to use OpenBloom/runtime-releases with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull OpenBloom/runtime-releases:Q4_K_M
Run and chat with the model
lemonade run user.runtime-releases-Q4_K_M
List all available models
lemonade list
- Atomic Chat
OpenBloom Runtime Releases
This repository hosts OpenBloom's self-built runtime artifacts β the engines and components that the OpenBloom desktop application provisions at install time. It contains no models: it hosts the runtime tooling that serves open-weight models locally, hash-pinned and verified on every download.
KrisKross 1.0.0
The KrisKross runtime bundle: OpenBloom's build of the MOSS-TTS inference runtime.
| Component | Source | License |
|---|---|---|
llama-moss-tts |
Built from OpenMOSS/llama.cpp at tag main-b8371-019bda3 |
MIT |
tokenizer.json |
OpenMOSS-Team/MOSS-TTS (Qwen3 backbone tokenizer) | Apache-2.0 |
MOSS-Audio-Tokenizer-ONNX (encoder + decoder) |
OpenMOSS-Team/MOSS-Audio-Tokenizer-ONNX | Apache-2.0 |
Verify before use β the bundle is hash-pinned by the OpenBloom downloader, and you can verify it yourself:
kriskross/1.0.0/kriskross-1.0.0-linux-amd64.tar.zst sha256: db50ea5521575cbbdcf13a5bfe2ba889d4b44b8b16c482cbec24d5a2d213c9a6
Every bundle ships a MANIFEST.json listing the sha256 of each
component, and a LICENSE describing the upstream licensing.
Attribution
KrisKross is OpenBloom's build of components authored by the OpenMOSS team and contributors. All credit for the upstream llama.cpp fork, the MOSS-TTS models and the MOSS Audio Tokenizer belongs to them. OpenBloom Labs produces the compiled bundle and publishes it for the OpenBloom installer.
Integrity policy
- Every artifact in this repository is public and fetchable unauthenticated, this is a requirement of the OpenBloom downloader.
- Every artifact is content-addressed: the consuming installer pins a sha256 and fails closed on any drift.
- Never gate this repository, and never rewrite a published version in place β publish a new versioned path instead.
- Downloads last month
- 63
4-bit