openjev/OpenJev-Flash-9B
Zero-Shot Classification • 9B • Updated • 269 • 1
The 9B decision model. About 1.6x faster than OpenJev, for text decisions.
Note BF16 weights for text decisions.
Note vLLM without load-time quantization.
Note llama.cpp builds from 5.6 GB.
Note 8-bit for Apple silicon.
Note 4-bit for smaller Macs.
A decision API over any open model, one pass per question
Note Serve the same decision API on your own GPU or Mac.