Cygnet local classifier scores 202/231 on DGX Spark
After waiting for a Hermes update that did not come, the author had an agent plan and test the Cygnet model, which scored 202/231 (87.4%) on the DGX Spark with p50 latency of 0.19s.
I was hopping Hermes would receive an emergency update and gift us with a open source local classifier JEV style but I guess that is not happening overnight so I decided to take the problem in my own hands. The first place in http://benchmarkheaven.com/jev-models is taken by Cygnet and it's creator @blockbrain_labs seems also interested in the subject so this is the model I will focus on. Asked my agent to plan it out and it did some preliminary testing and the model seems to work pretty well on the DGX Spark at the same time with Qwen 3.8 27B. Score 202 / 231 (87.4%) — target was ≥198 ✅ vs recipe reference204/231 on bf16, so QAT is within ~2 pts of full precision Per-question latency p50 0.19 s, p95 1.3 s