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.
LatestSenseTimeU1.5
SenseTimeAny-to-Any

SenseTime Releases SenseNova U1.5 8B Any-to-Any Model

The new 8B multimodal model handles text, images, and image editing within a single native architecture.

Aug 19, 2026
NotableOther
SenseNova-U1.5-8B-MoT

SenseTime has published SenseNova-U1.5-8B-MoT, an 8-billion-parameter multimodal model that treats different media as first-class citizens rather than bolting a vision encoder onto a text backbone. The release is available now on Hugging Face.

The headline feature is its any-to-any design. Where many open models specialize in reading images or writing text, U1.5 is built to move fluidly across modalities, including native image generation and image editing alongside its language capabilities.

Why it matters

Unified multimodal models have become a competitive frontier, with the appeal being a single set of weights that can understand and produce across formats without stitching together separate systems. Doing that at an 8B scale is notable, since it keeps the model within reach of researchers and developers who cannot run the largest frontier systems.

  • Native any-to-any handling across text and images
  • Built-in image generation and editing
  • 8B parameters, a practical size for local and small-cluster use

A few important details are not spelled out in the release record, including context length and the exact licensing terms, which are listed simply as "other." Anyone planning production use should check the model card for usage restrictions before building on it. For now, U1.5 marks SenseTime's entry into the growing field of compact, genuinely multimodal open models.

Sources

  • sensenova/SenseNova-U1.5-8B-MoT

    Hugging Face

    Visit
OlderAudio8 debuts a compact 0.1B preview TTS modelAudio8 · Text → Speech · 3 months agoNewerLiquid AI's LFM2.5-DSpark targets faster inferenceNVIDIA · Text / LLM · 3 months ago

Get the model

Hugging Face

Specs

Parameters8B
Context window262K tokens
PrecisionBF16
ArchitectureNEOChatModel
LicenseOTHER
Downloads710
Likes295

Can you run it?

Runs on a laptop — about 7.2 GB at 4-bit.

  • BF16 (as published)

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

    18.4 GB
  • 8-bit

    12 GB GPU (RTX 3060 / 4070) · 16 GB Mac

    10.9 GB
  • 4-bit

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

    7.2 GB
Your machine
GGUF builds
  • Parameter count is an editorial estimate — no weights metadata on Hugging Face.
  • KV cache sized for 8,192 tokens of context; longer prompts need proportionally more.

Estimated from the parameter count. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Any-to-Any
3 versions — view changelog

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 SenseTime

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

SenseTime previews a 9B looped-transformer VLM

SenseNova-Loop-9B-Preview puts a recurrent-depth architecture to work on multimodal reasoning.

Oct 28, 2026
SenseTime/Any-to-AnyRuns on a laptop

SenseTime's SenseNova-U1.5 Unifies Vision Tasks

An 8B model drops the usual encoder and VAE in favor of a single native architecture spanning understanding, reasoning, and image generation.

Sep 9, 2026

More in Any-to-Any

All Any-to-Any →
Sage S2.1 Flash
Internlm/ReasoningMulti-GPU server

InternLM's Sage S2.1 Flash targets scientific reasoning

The 320B mixture-of-experts model is built to reason over scientific evidence and act inside interactive environments.

Nov 15, 2026
Haru-4B
Higurashi Ai/Any-to-AnyRuns on a laptop

Haru-4B Brings Full-Duplex Speech to Six Languages

A compact 4-billion-parameter model handles real-time, two-way voice conversation across six languages in a single system.

Nov 12, 2026
LongCat 2.5
Meituan/Text / LLMDatacenter

Meituan Releases LongCat 2.5, an MIT-Licensed MoE

The Chinese delivery giant expands its open-model push with a multimodal, agentic mixture-of-experts system.

Nov 4, 2026