Text Generation
cortiq
English
Chinese
cmf
quantized
q2tp
q4tp
mixed-precision
Mixture of Experts
hybrid-attention
2-bit
4-bit precision
Instructions to use infosave/GLM-5.3-Flash-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/GLM-5.3-Flash-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/GLM-5.3-Flash-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
-
Refresh GLM Q2TP and Q4TP performance evidence
Verified signatureb05a511 -
Refresh GLM Q2TP and Q4TP performance evidence
Verified signature5590d8e -
Document GLM-5.3-Flash Q2TP and bounded runtime
Verified signature09eca95 -
Add GLM-5.3-Flash Q2TP CMF
Verified signature84a2b57
-
Document measured Q4TP CPU and 16 GB policy
Verified signatureea719eb -
Add files using upload-large-folder tool
Verified signature4cbf776 -
Add GLM-5.3-Flash CMF model card
Verified signature1bc3feb -
initial commit
Verified signatureb9a32b3