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.
Omar (kouhxp)'s CPU decision model: a Qwen3.5-0.8B fine-tune shipped as GGUF for llama.cpp that answers yes/no, choice and score questions with a probability per option plus a 'none of these' reject probability, served by a local Jev-style HTTP runtime.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
gutsy
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-0.8b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
73.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 gutsy?
clm is from Contrastive-LM and gutsy from Omar (kouhxp). Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. gutsy is the smaller model, at 800M parameters to 8.0B.
Which is more accurate, clm or gutsy?
Only gutsy publishes an accuracy figure (73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or gutsy?
clm: Free (open weights). gutsy: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or gutsy locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull kouhxp/gutsy download the weights.
—
Evaluation suite
—
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
