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.
LatestTencent4-flash
TencentVision-Language

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
NotableOther
Hunyuan Hy4-flash

Tencent has quietly released Hunyuan Hy4-flash, a new multimodal model in its Hunyuan family, now available on Hugging Face. The "flash" branding signals a model tuned for speed and efficiency, aimed at latency-sensitive workloads rather than maximum capability.

The release is built around a mixture-of-experts (MoE) architecture, which activates only a portion of the model's parameters for any given input. That approach lets developers tap a large total parameter pool while keeping inference costs closer to those of a smaller dense model — a practical fit for the "flash" positioning.

What it does

Hy4-flash is a vision-language model with text capabilities, meaning it can take in both images and text and respond to instructions. Key points from the record:

  • Primary modality is vision-language, with text handling alongside
  • MoE design for efficient inference
  • Released as an instruction-tuned model under a custom (non-standard) license

Specifics such as parameter counts and context length were not detailed in the release metadata, so teams evaluating the model will want to check the model card directly for configuration and usage terms.

Why it matters: Tencent is one of several large Chinese labs steadily shipping open-weight models, and a fast multimodal MoE broadens the options for developers who need image understanding without the overhead of a frontier-scale system. As always, the custom license means the details of commercial use deserve a close read before deployment.

Sources

  • tencent/Hy4-flash

    Hugging Face

    Visit
OlderApple's FastFrames-L Targets Real-Time Video GenerationApple · Text → Video · 4 days agoNewerSenseTime Releases Looped 9B Multimodal ModelSenseTime · Vision-Language · 3 days ago

Get the model

Hugging Face

Specs

Context window1.0M tokens
Size440.5 GB
PrecisionBF16
ArchitectureHYV4FlashForConditionalGeneration
LicenseOTHER
Downloads3.9K
Likes482

Can you run it?

Needs a multi-GPU server — about 133.4 GB at 4-bit.

  • BF16 (as published)

    8×H100 80 GB node

    441.9 GB
  • 8-bit

    4×H100 80 GB · 512 GB Mac Studio

    234.6 GB
  • 4-bit

    2×H100 80 GB · 256 GB Mac Studio

    133.4 GB
Your machine
GGUF builds
  • Mixture-of-experts: every expert must be loaded, so memory follows total parameters, not the active slice.
  • 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

Text / LLMVision-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 Tencent

All Tencent releases →
Hunyuan Hy4
Tencent/Text / LLMDatacenter

Tencent releases Hunyuan Hy4, an MoE vision-language model

The instruction-tuned, mixture-of-experts model handles both images and text under an open weights listing on Hugging Face.

Oct 29, 2026
Hy-Nomas
Tencent/Text → Video

Tencent Releases Hy-Nomas, an Interactive Video World Model

The open-weights model pairs text- and image-to-video generation with action-aware causal attention and explicit camera control.

Oct 21, 2026
Hy-Memory 30B-A3B
Tencent/Text / LLMConsumer GPU

Tencent releases Hy-Memory 30B-A3B under Apache 2.0

A memory-focused mixture-of-experts model activates just 3B of its 30B parameters per token, and ships with a permissive license.

Oct 15, 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
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
Inkling-2-Small
Thinkingmachines/Vision-LanguageMulti-GPU server

Thinking Machines ships Inkling-2-Small, an open MoE VLM

The Apache-2.0 vision-language model uses a mixture-of-experts design and lands openly on Hugging Face.

Nov 4, 2026