deck31b (Gemma 4 31B)
deck31b (Gemma 4 31B) by krishna-gogineni-765 is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 59.0 on the Jev Decision Index (rank 12).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- krishna-gogineni-765
- Parameters
- 33B
- Released
- Oct 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Decoder LM with a decision readout
- Backbone
- google/gemma-4-31B-it
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- —
Benchmarks
- Jev Decision IndexECE 0.204
- 59.0
Jev Decision Index: public 58.2, ECE 0.204, Brier 0.469. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare deck31b (Gemma 4 31B) with…
FAQ
How much does deck31b (Gemma 4 31B) cost?
deck31b (Gemma 4 31B) has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can deck31b (Gemma 4 31B) answer?
deck31b (Gemma 4 31B) answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is deck31b (Gemma 4 31B) well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.204; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is deck31b (Gemma 4 31B) open weight, and can it run on a CPU?
Yes, deck31b (Gemma 4 31B) has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Benchmark Heaven JevBench). Pricing is per 1M tokens (USD); confirm with the provider before production use.