Jolt-4B

mlengineer-aiDecision modelOpen weights

Jolt-4B by mlengineer-ai is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

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

Specifications

Provider: mlengineer-ai
Parameters: 4B
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/Qwen3.5-4B
Jev-compatible request: No
Runs on CPU: No
License: cc-by-nc-sa-4.0
Hugging Face: mlengineer-ai/Jolt-4B

Compare Jolt-4B with…

Jolt-4B vs amos-1-large—/1M in Jolt-4B vs amos-1-medium—/1M in Jolt-4B vs Celeris-1 Decision$0.04/1M in Jolt-4B vs ScaleDown Classify-1$0.04/1M in Jolt-4B vs Cloudflare clef—/1M in Jolt-4B vs Cloudflare clef-flash—/1M in

FAQ

How much does Jolt-4B cost?

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

What questions can Jolt-4B answer?

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

Is Jolt-4B well calibrated?

No calibration measurement for Jolt-4B is recorded yet.

Is Jolt-4B open weight, and can it run on a CPU?

Yes, Jolt-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 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.