vLLM-SR d3-edge (0.6B)
vLLM-SR d3-edge (0.6B) 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 20.2 on the Jev Decision Index (rank 124).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- vLLM Semantic Router
- Parameters
- 594M
- 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
- Qwen/Qwen3.5-0.8B
- Jev-compatible request
- Yes
- Runs on CPU
- Yes
- License
- apache-2.0
- Hugging Face
- vllm-sr/d3-edge
Benchmarks
- Jev Decision IndexECE 0.141
- 20.2
- Jev Decision Index — VisionECE 0.098
- 31.7
Jev Decision Index: public 28.8, ECE 0.141, Brier 0.585. 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 0.3 kit (release-v3), self-run
- 28.8
Speed & latency
Compare vLLM-SR d3-edge (0.6B) with…
FAQ
How much does vLLM-SR d3-edge (0.6B) cost?
vLLM-SR d3-edge (0.6B) has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can vLLM-SR d3-edge (0.6B) answer?
vLLM-SR d3-edge (0.6B) answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is vLLM-SR d3-edge (0.6B) well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.141; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is vLLM-SR d3-edge (0.6B) open weight, and can it run on a CPU?
Yes, vLLM-SR d3-edge (0.6B) has open weights. It is small enough to run on a CPU.
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.