Meta · Llama 3.2

Llama 3.2 90B Vision Instruct

READER SUMMARY

The aligned 90-billion-parameter Llama 3.2 multimodal flagship for advanced visual reasoning, image-grounded dialogue, document analysis, and customizable local or cloud deployment.

DOOM SCORE67.7out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 67.7

Strong instruction-following visual reasoning plus downloadable weights create high capability, meaningful agentic use, broad misuse exposure, and difficult post-release control despite substantial compute requirements.

Capability74
Autonomy32
Deployment88
Misuse potential70
Control difficulty75
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 3.2 90B Vision Instruct

The model score of 67.7 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.00

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

CapabilityTOWARD

Meta releases Llama 3.2 vision and edge models

Meta released eight Llama 3.2 checkpoints spanning 1B and 3B text models for on-device tool use and 11B and 90B vision models, with downloadable weights and immediate cloud, device, and local ecosystem support.

Full item contribution
+0.03
Llama 3.2 90B Vision Instruct equal share
+0.00
Read assessment →
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 67.7

    New exact open Llama 3.2 vision instruction flagship verified by Meta's dated launch.

    12 Aug 2026