Revesery
Dashboard
Home
Explore
Groups
Jobs
Tools
Rewards
Social Media
VideoBulk VideoProfile PictureSlide ShowSound / AudioUnfollowersDouyin
VideoBulk Video
VideoStoriesBulk VideoProfile PictureSlide ShowUnfollowersStalker CheckSoon
VideoUnfollowersLink Cleaner
MP4 · VideoMP3 · Audio
WhatsApp
Profile PictureCover Art & Preview
Profile Picture
Video & Image
Video & Photo
Utilities
AI Chat
Fake SNBTWatermark KTP
TeraboxVidey
Deep Voice CheckerReview Calculator
Surat IzinFoto Hijau Biru MerahQR GeneratorSoon
Case ConverterCookie Converter
Request a toolImage ToolsSoonText ToolsSoon
Premium
Soon
Add bookmarks
Revesery
HomeExploreGroupsJobsContributors
Most read
↑↓ selectEnter openEsc close/ to search from anywhere
Login
J
JenExplorer
@jen · Oct 7, 2026 · 146 views
#News

llama.cpp Now Runs Decision Models

Every agent loop hits the same wall: something has to pick one option out of a handful. Which queue does this ticket belong in, does this comment stay up, what does the agent do next. llama.cpp can now run models built for exactly that job.

The support is already there for five open models, and they span a huge range of sizes — from 144M up to 27B parameters — with more coming.

llama.cpp Now Runs Decision Models

What Happened

llama.cpp added support for decision models. Instead of writing you a paragraph and leaving you to guess what it meant, these models take a typed question and hand back a probability for every option you offered.

The tasks the source names are the everyday ones: routing tickets, moderating content, and choosing an agent's next step. Five open models are supported so far, running from 144M to 27B parameters. More are on the way.

Why It Matters

A chat model gives you text, and then you write a parser to turn that text into a decision. Decision models skip the parsing step — the output is already a number per option, so your code can compare them and move on.

The size range is the other half of it. A 144M model and a 27B model are not the same machine's problem, so you can pick how much hardware this part of your pipeline is allowed to eat. For anyone already running llama.cpp locally, this is a new category of model to try without adding a new tool to the stack.

Liked Jen's share? Revesery is where people swap what they're actually building.

Join with Google

Comments

Join the conversation — sign in to comment.

Sign In Now

No comments yet — start the conversation!

Read it later?
We'll email you the link to this share. Nothing else.

More shares you might like

AIboss-skill Turns AI Coding Agents Into a Full Dev TeamJen · 16h · 25 viewsAIStand With Jensen Petition Passes 89,000 SignaturesJen · 1d · 36 viewsAIHow to Break Down Any Video With rea-videoJen · 2d · 51 viewsAIHow to Claim 1 Month of SuperGrok for FreeJen · 4d · 76 viewsNews500+ AI Agent Projects Land on GitHub With 39K StarsJen · 4d · 63 viewsToolsHow to Sign Up for Amazon Associates on Your PhoneJen · 5d · 57 views

Trending this week

Ranked by how many people read each share in the last 7 days, each person counted once. Bots, the author and clicks from this list don't count. Shares from the last 14 days with a real write-up. Refreshed every 5 minutes.
  1. 1How to Get 2 Years of Google AI Pro Free@jen127 views this week
  2. 2How to Claim 1 Month of SuperGrok for Free@jen44 views this week
  3. 3How to Claim 20,000 Free Clocked AI API Credits@jen44 views this week
  4. 4Harness Tweaks Change Agent Cost 2.6x, Accuracy Barely Moves@alex43 views this week
  5. 5How to Make a Ghostly Abandoned Village Video With AI@alex43 views this week
See more on Explore

Site footer

Revesery

Empowering people to share valuable insights, discover hidden information, and connect with an amazing community of learners and experts.

  • 722Members
  • 866Shares published

Explore

  • Explore shares
  • Top contributors
  • Feedback

Company

  • About us
  • Editorial policy
  • Contact
  • Advertise with us
  • System status
© 2026 Revesery
  • Privacy
  • Terms
  • Trust & Safety
  • DMCA
HomeExploreShareToolsProfile
BABabar Azam joined Revesery7 hours ago