The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestCloudflareClairic
CloudflareVision-Language

Cloudflare's Clairic Targets Structured Data Extraction

A new multimodal model from Cloudflare focuses on turning documents and images into clean, structured output.

Oct 16, 2026
UpdateOther
Clairic

Cloudflare has published Clairic, a multimodal (vision-language) model aimed squarely at a practical problem: pulling clean, structured data out of messy inputs. Rather than chasing general chat benchmarks, the model is pitched for information extraction and structured output, according to its Hugging Face repository.

What it's for

Structured extraction is one of the least glamorous but most valuable jobs in applied AI. Enterprises routinely need to convert invoices, forms, screenshots, and scanned documents into predictable JSON or tabular records. A model tuned for that task can save teams from brittle regex pipelines and one-off OCR glue code.

Key points from the release:

  • Clairic is a vision-language model, so it can reason over images alongside text.
  • Its stated focus is structured output and information extraction rather than open-ended generation.
  • It is distributed under a custom ("other") license, so teams should check the terms before production use.

The release leaves several technical details unspecified, including parameter count and context length, so prospective users will want to validate accuracy and throughput on their own documents before committing.

Why it matters

Cloudflare has been steadily building out its Workers AI platform, and an in-house extraction model fits neatly into that strategy. If Clairic performs well on real-world documents, it could give developers a lightweight, deployable option for turning unstructured media into usable data without stitching together multiple services.

Sources

  • Cloudflare/clairic

    Hugging Face

    Visit
OlderOrnith AI releases 122B MoE multimodal model under MITOrnith Ai · Text / LLM · last monthNewerNVIDIA releases compact Dory 1.0 4B text modelNVIDIA · Text / LLM · last month

Get the model

Hugging Face

Specs

Context window262K tokens
Size55.6 GB
PrecisionBF16
ArchitectureQwen3_5ForConditionalGeneration
LicenseOTHER
Downloads727
Likes219

Can you run it?

Runs on a 24 GB GPU at 4-bit.

  • BF16 (as published)

    80 GB GPU (A100 / H100) · 128 GB Mac Studio

    58.7 GB
  • 8-bit

    48 GB GPU (RTX 6000) or 2×24 GB · 64 GB Mac

    32.6 GB
  • 4-bit

    24 GB GPU (RTX 3090 / 4090) · 32 GB Mac

    19.8 GB
Your machine
GGUF builds
  • KV cache sized for 8,192 tokens of context; longer prompts need proportionally more.

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Vision-Language

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Cloudflare

All Cloudflare releases →
Clef
Cloudflare/Vision-LanguageConsumer GPU

Cloudflare's Clef brings structured decisions to open models

The new open-weight vision-language family outputs typed, structured results and arrives alongside a reinforcement-learning fine-tuning platform.

Oct 1, 2026
Cloudflare/Text / LLM

Cloudflare releases Clef open-weight decision models

The company pairs its new Clef family with a reinforcement-learning fine-tuning platform aimed at action-oriented tasks.

Oct 1, 2026

More in Vision-Language

All Vision-Language →
SenseNova-Loop-9B
SenseTime/Vision-LanguageRuns on a laptop

SenseTime Releases Looped 9B Multimodal Model

The company's new SenseNova-Loop-9B pairs vision-language capabilities with a recurrent looped-transformer design.

Nov 17, 2026
Hunyuan Hy4-flash
Tencent/Vision-LanguageMulti-GPU server

Tencent releases Hunyuan Hy4-flash multimodal MoE

The lightweight, mixture-of-experts model adds vision and text instruction-following to Tencent's open Hunyuan lineup.

Nov 17, 2026
Inkling 2 Mini
Thinkingmachines/Vision-LanguageConsumer GPU

Thinking Machines releases Inkling 2 Mini, a compact open MoE

The Apache-2.0 multimodal model uses a mixture-of-experts design aimed at running locally rather than in the cloud.

Nov 17, 2026