ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.
Private assistant you host yourself
Find a commercially usable open-weights assistant that you can operate yourself.
Worked example as of 2026-09-23, from the public data image.
Open weights you run yourself; commercial licence.
Requirements
model.class = text-generator: A conversational assistant needs a text-generating model.model.weights_openness = open_weights: Self-hosting requires downloadable weights; add a model.fits_hardware Must for the device you own.licence.commercial_use in {permitted, permitted_with_conditions}: The licence must allow commercial use, including use with stated conditions.
Preferences
chat_preference: Prefer assistants whose open-ended responses people rate more highly.-offering.cost_per_task: Prefer lower task cost when the snapshot has an offering price.
Applied template spec
spec_version- 1
where- model.class = text-generator
- model.weights_openness = open_weights
- licence.commercial_use in {permitted, permitted_with_conditions}
optimizeweightschat_preference- 0.7
-offering.cost_per_task- 0.3
Worked answer
Decision status: partial.
Separated on the evidence
zhipu/glm-5-3
probability bands: a model joins the leader when P(its score >= the leader's) >= 0.25 under the score posteriors; a weighted capability with an 80% interval wider than 2.8 is not enough evidence
This is a partial answer. Unknown facts or missing objective evidence can leave eligible candidates unranked.
probability bands: a model joins the leader when P(its score >= the leader's) >= 0.25 under the score posteriors; a weighted capability with an 80% interval wider than 2.8 is not enough evidence
Score and score interval use the objective's dimensionless normalised units. Cost per task is for the engine-selected offering and the applied spec's task size. When task size is omitted, the engine uses its documented default. P(best) is the engine probability. Unavailable means the engine did not return a value. Thin evidence is undetermined and is not a recommendation.
Best band
| Model | Score | Score interval | P(best) | Cost per task, USD | Capability estimates and intervals |
|---|---|---|---|---|---|
zhipu/glm-5-3 | 0.613076 | [0.512916, 0.713236] | 1.0 | 0.0736 |
|
Rest band
| Model | Score | Score interval | P(best) | Cost per task, USD | Capability estimates and intervals |
|---|---|---|---|---|---|
deepseek/deepseek-v4-pro | 0.323141 | [0.222982, 0.423301] | 0.0 | 0.06864 |
|
zhipu/glm-5-2 | 0.260698 | [0.160538, 0.360857] | 0.0 | 0.0736 |
|
Unknown requirements
Some candidates may qualify. Missing facts:
model.weights_opennessoffering.cost_per_task
Engine warnings
- not_separable
Decision dec_180a6dc921c00532eceebd84 on public snapshot snap_05a963d2477ac2fb.
What this template teaches
Use Must for deployment and licence requirements, then Prefer to balance assistant quality and cost. Lab jurisdiction is a buyer-set Must (origin.lab_jurisdiction in {…}); an unverified jurisdiction does not pass, so set the countries on the facet board. The same condition works as an inventory profile rule.
The live board uses current data. Its answer can change as evidence changes.
Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.