Skip to content

vLLM-SR Decision 2.0 Nox 4B

vLLM Semantic RouterDecision modelOpen weights

vLLM-SR Decision 2.0 Nox 4B by vLLM Semantic Router is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 45.0 on the Jev Decision Index (rank 65).

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
vLLM Semantic Router
Parameters
4B
Released
Sep 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
Qwen/Qwen3.5-4B-Base
Jev-compatible request
Yes
Runs on CPU
No
License
apache-2.0
Hugging Face
vllm-sr/Decision-2.0-Nox-4B

Benchmarks

Jev Decision IndexECE 0.030
45.0

Jev Decision Index: public 44.2, ECE 0.030, Brier 0.436. Lower ECE means its probabilities can be taken at face value.

Self-reported by the publisher

The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.

Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.2.1 kit (release-v2.1), self-run
43.8

Speed & latency

Median latency per call (Decision Index)
34 ms

Compare vLLM-SR Decision 2.0 Nox 4B with…

FAQ

How much does vLLM-SR Decision 2.0 Nox 4B cost?

vLLM-SR Decision 2.0 Nox 4B has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can vLLM-SR Decision 2.0 Nox 4B answer?

vLLM-SR Decision 2.0 Nox 4B answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is vLLM-SR Decision 2.0 Nox 4B well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.030; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is vLLM-SR Decision 2.0 Nox 4B open weight, and can it run on a CPU?

Yes, vLLM-SR Decision 2.0 Nox 4B 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, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.