# decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs garas (Gemma 4 31B)

As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads garas (Gemma 4 31B) in 1 of 1 shared categories: Decision models.

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): price per 1M tokens is unset in the catalog.

garas (Gemma 4 31B): price per 1M tokens is unset in the catalog.

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): open weights.

garas (Gemma 4 31B): open weights.

- Which to pick, Decision models: As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads garas (Gemma 4 31B) in Decision models at #4 against #30.

As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) is state of the art in Decision models (since Oct 8, 2026; sources JevBench price; methodology v1.0).

As of Oct 14, 2026, garas (Gemma 4 31B) is ranked #30 in Decision models (since Oct 14, 2026; sources Decision Index Full; methodology v1.0).