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.
LatestLiquidAI2.5-VL
LiquidAIVision-Language

Liquid AI's LFM2.5-VL-3B targets on-device vision

The 3-billion-parameter vision-language model is tuned for faster multimodal work on edge hardware.

Aug 12, 2026
NotableOther
LFM2.5-VL-3B

Liquid AI has released LFM2.5-VL-3B, a compact vision-language model designed to run multimodal workloads directly on edge hardware rather than in the cloud. At roughly 3 billion parameters, the model is small enough to fit on consumer and embedded devices while still handling combined image and text inputs, according to the company's announcement on Hugging Face.

The pitch is speed and locality. Liquid AI frames LFM2.5-VL-3B as an option for developers who want faster vision capabilities without shipping user data to a remote server — a trade-off that matters for latency-sensitive applications, privacy-conscious deployments, and settings with limited connectivity.

Why it matters

Most capable vision-language models are large and cloud-bound, which makes on-device multimodal inference a persistent bottleneck. A 3B model that keeps quality reasonable while improving throughput fits a growing niche:

  • Real-time image understanding on phones and embedded systems
  • Offline or intermittent-connectivity environments
  • Applications where sending images off-device is a non-starter

The model ships under a custom license, so teams evaluating it for production should check the terms before building on top of it. As an entry point for Liquid AI's LFM2.5-VL line, it signals the company's continued focus on efficient models tuned for the edge rather than raw frontier scale.

Sources

  • LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

    Announcement

    Visit
  • LiquidAI/LFM2.5-VL-3B

    Hugging Face

    Visit
OlderNVIDIA Opens Magpie TTS for Multilingual Voice AgentsNVIDIA · Text → Speech · 3 months agoNewerSuperwhisper's s1-mini polishes raw speech-to-text outputSuperwhisper · Speech → Text · 3 months ago

Get the model

Hugging FaceAnnouncement

Specs

Parameters3B
Context window33K tokens
Size6.2 GB
PrecisionBF16
ArchitectureLfm2VlForConditionalGeneration
LicenseOTHER
Downloads45.2K
Likes239

Can you run it?

Runs on just about anything.

  • BF16 (as published)

    8 GB GPU (RTX 4060) · 16 GB laptop or Mac

    7.7 GB
  • 8-bit

    8 GB GPU (RTX 4060) · 16 GB laptop or Mac

    4.8 GB
  • 4-bit

    Any modern laptop · 8 GB RAM

    3.4 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 LiquidAI

All LiquidAI releases →
LFM3-1.7B
LiquidAI/Text / LLMRuns anywhere

Liquid AI debuts LFM3-1.7B for edge deployment

A compact 1.7B-parameter multilingual model built to run locally and serve as the base for specialized multimodal variants.

Oct 23, 2026
LFM3-Omni-2B
LiquidAI/Any-to-AnyRuns anywhere

Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge

The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.

Oct 21, 2026
LFM2.5-24B-A2B
LiquidAI/EmbeddingsConsumer GPU

Liquid AI's LFM2.5 Puts a 24B MoE on Your Device

The new mixture-of-experts model keeps total capacity high while activating only about 2B parameters per token for edge agents.

Oct 12, 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
Mirage
Cactus Compute/Vision-Language

Cactus Compute's Mirage brings vision tasks on-device

The new open vision-language model targets detection, segmentation, and visual Q&A without relying on the cloud.

Nov 5, 2026