# Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) vs Decider 31B (NVFP4)

As of Oct 15, 2026, Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) leads Decider 31B (NVFP4) in 0 of 1 shared categories.

Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted): price per 1M tokens is unset in the catalog.

Decider 31B (NVFP4): price per 1M tokens is unset in the catalog.

Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted): open weights.

Decider 31B (NVFP4): open weights.

- Which to pick, Decision models: As of Oct 15, 2026, Decider 31B (NVFP4) leads Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) in Decision models at #2 against #23.

As of Oct 15, 2026, Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) is ranked #23 in Decision models (since Oct 15, 2026; sources JevBench; methodology v1.0).

As of Oct 15, 2026, Decider 31B (NVFP4) is near state of the art, rank #2 in Decision models (since Oct 15, 2026; sources Decision Index Full; methodology v1.0).