Text Generation
cortiq
English
Russian
Chinese
cmf
quantized
q4tp
Mixture of Experts
looped-transformer
reasoning
tool-calling
cuda
vulkan
metal
Instructions to use infosave/Inkling-2-Mini-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Inkling-2-Mini-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/Inkling-2-Mini-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
Commit History
Today
-
Card: cortiq 0.9.15 numbers (RTX PRO 6000 CUDA, M4 Metal)
Verified signature6c9d659 -
Inkling-2-Mini-q4tp.cmf with the release DSpark drafter; card for cortiq 0.9.14 (DSpark, RTX PRO 6000 Blackwell, new speeds)
Verified signaturedf22ba1
Yesterday
-
Inkling-2-Mini-q4tp.cmf: q4tp experts, GPTQ dense trunk, 8-bit head
Verified signaturef61c7f2 -
Inkling-2-Mini CMF: card (EN/RU/ZH), figures, license, checksum
Verified signatureff7a881 -
initial commit
Verified signature1f487c0