Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
rizzo-flow
Fine-tuned from
qwen/qwen3-8b
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
—
195 ms
p95 latency
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between clm and rizzo-flow?
clm is from Contrastive-LM and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. rizzo-flow is the smaller model, at 4.0B parameters to 8.0B.
Which is more accurate, clm or rizzo-flow?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or rizzo-flow?
clm: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or rizzo-flow locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
—
Evaluation suite
—
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
