Tuesday17 Nov 2026
MachinePulse open-sources Karpo Decision 31B single-pass decision models
Released under Apache 2.0 on Hugging Face (research blog dated 13 November 2026), scoring 73.9 on Decision Index Full at 95 ms median RTX PRO 6000 latency.
Open sourceStory 16 of the day
60-second takeaway: MachinePulse releases six Apache 2.0 Karpo Decision models (0.8B to 31B) that return calibrated multi-question probabilities in one forward pass.
Why it matters: Answering many structured routing, moderation or ranking questions in one 95 ms pass on a single workstation GPU avoids autoregressive token generation overhead.
- Model family and licence
- Six open-weight checkpoints from 0.8B to 31B (31B built on Gemma 4 31B) under Apache 2.0
- Context and serving interface
- 32,768 tokens per sequence; Python API, Transformers pipeline and System One HTTP (POST /v1/systemone)
- Benchmark and latency
- 73.9 Decision Index Full (#1 of 300); 87.2 JevBench Capability (#3 of 243 open-weight); 95 ms median on 1x RTX PRO 6000

