# decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune)

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 torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune) 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.

torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune): 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.

torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune): 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 torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune) in Decision models at #4 against #8.

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, torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune) is ranked #8 in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench; methodology v1.0).