Instructions to use infosave/Ternary-Bonsai-2-27B-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Ternary-Bonsai-2-27B-cmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/Ternary-Bonsai-2-27B-cmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq run FILE.cmf --prompt "What is the capital of France?"
cortiq serve FILE.cmf --port 8080 # OpenAI-compatible server
- Notebooks
- Google Colab
- Kaggle
Build Cortiq 0.6.9
Use the published release tag; do not apply the historical 0.6.8 development patch to this version.
git clone --branch v0.6.9 --depth 1 https://github.com/infosave2007/cmf.git
cd cmf
cargo build --locked --release -p cortiq-cli --features gpu
./target/release/cortiq --version
Alternatively:
cargo install cortiq-cli --version 0.6.9 --locked --features gpu
Use a current stable Rust toolchain, normal platform compiler/linker prerequisites, and a working Vulkan driver on Linux. Native Metal is used on Apple Silicon. Follow the model card's backend-specific environment and verification commands.
The model bytes have not changed. Earlier files under source/patches/ and the historical provenance record describe development measurements before release; they are archived evidence, not patches to install over 0.6.9.
Quality/throughput numbers in the model card identify their measured development paths. Cross-platform release compilation is not a performance benchmark on every target.