Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Qwen3.5-4B-Hmm

n4ze3mDecision modelOpen weights

Qwen3.5-4B-Hmm by n4ze3m 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
n4ze3m
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
Jev-compatible request
No
Runs on CPU
No
License
apache-2.0
Hugging Face
n4ze3m/Qwen3.5-4B-Hmm

Compare Qwen3.5-4B-Hmm with…

Qwen3.5-4B-Hmm vs amos-1-large—/1M inQwen3.5-4B-Hmm vs amos-1-medium—/1M inQwen3.5-4B-Hmm vs Celeris-1 Decision$0.04/1M inQwen3.5-4B-Hmm vs ScaleDown Classify-1$0.04/1M inQwen3.5-4B-Hmm vs Cloudflare clef—/1M inQwen3.5-4B-Hmm vs Cloudflare clef-flash—/1M in

FAQ

How much does Qwen3.5-4B-Hmm cost?

Qwen3.5-4B-Hmm has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Qwen3.5-4B-Hmm answer?

Qwen3.5-4B-Hmm answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Qwen3.5-4B-Hmm well calibrated?

No calibration measurement for Qwen3.5-4B-Hmm is recorded yet.

Is Qwen3.5-4B-Hmm open weight, and can it run on a CPU?

Yes, Qwen3.5-4B-Hmm 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.