Tencent Hy(@TXhunyuan)

Introducing Hy3D WorldClaw——an agentic workflow that generates large scale 3D open worlds from text...

Tencent Hy (@TencentHunyuan) — Tue, 11 Aug 2026 06:48:22 GMT

Introducing  Hy3D WorldClaw——an agentic workflow that generates large scale 3D open worlds from text prompts.🚀🚀🚀
Not video, Not Gaussian Splatting, Every scene generated by WorldClaw is freely explorable and built entirely from editable, game-ready 3D assets with high-quality geometry and textures.
Project Pagtencent-hunyuan.github.io/Hunyuan3D-Worl…b1S

Your browser does not support the video tag.

💬79🔄260❤️2491👀222686📊828

3⃣3⃣3⃣

Tencent Hy (@TencentHunyuan) — Thu, 06 Aug 2026 07:36:27 GMT

3⃣3⃣3⃣

Tencent 腾讯@TencentGlobal

Built for practical AI, Tencent Hy3 combines flagship-level performance with a compact, cost-efficient design. Bringing advanced reasoning and agent capabilities to research, coding, office productivity, design and cloud workflows.

Now available globally across Tencent products, APIs and developer platforms.

Try Hy3 today.
Hy3 Official Website: hy.tencent.ai
Hy3 API Pricing: openrouter.ai/tencent/hy3
Tencent WorkBuddy: workbuddy.ai
Tencent Design Miora: miora.design
Tencent Cloud TokenHub: tencentcloud.com/products/token…

Your browser does not support the video tag.

💬5🔄4❤️124👀15475📊19

🚀 Hy3 is now live in WorkBuddy global—free for users worldwide through August 31, 2026 (PT). Resea...

Tencent Hy (@TencentHunyuan) — Wed, 05 Aug 2026 02:59:51 GMT

🚀 Hy3 is now live in WorkBuddy global—free for users worldwide through August 31, 2026 (PT).

Research, analyze data, create documents and presentations, and handle workplace communications in an agentic AI workspace—no setup required.

Hy3 is also available through Tencent Design Miora and Tencent Cloud TokenHub.

Try it:workbuddy.air
#TencentHyy#Hy33#WorkBuddyy#Mioraa#TencentCloudd

💬30🔄58❤️396👀151319📊133

AI that finally hears you. 👂 Hy ASR 3.0 preview drops today. Powered by Hy3’s language brain → ...

Tencent Hy (@TencentHunyuan) — Tue, 04 Aug 2026 09:58:55 GMT

AI that finally hears you. 👂

Hy ASR 3.0 preview drops today. 

Powered by Hy3’s language brain 
→ precision ASR + deep semantic understanding

Wins on:
• general recognition
• context awareness
• multi-scenario robustness
• dialect coverage

Messy real-world audio? Clean, coherent transcripts that nail your intent. 

Open + internal benches: leading.
Multilingual WER ≈ 3%. 

Voice just got an upgrade. 🔥#HyASRS#TencentAIA#Hy3y3

💬23🔄28❤️455👀28957📊120

Hy-MT2 keeps gaining momentum. Since its open-source release in May: → 700K+ downloads 🌟 → Hy-MT2-...

Tencent Hy (@TencentHunyuan) — Fri, 31 Jul 2026 08:32:29 GMT

Hy-MT2 keeps gaining momentum.

Since its open-source release in May:
→ 700K+ downloads 🌟
→ Hy-MT2-1.8B reached #1 on the Hugging Face trending, with 30B-A3B reaching #4 🥇
→ 70+ verified product and project integrations 💻
→ Broader Hy-MT ecosystem support across Apple MLX-LM, Microsoft ONNX Runtime, NVIDIA NeMo, LLaMA-Factory, and more 👯
→ Real-world adoption, including real-time multilingual translation of livestream comments on Bilibili 📺

And now, Hy-MT2-30B-A3B is officially available in GGUF format—addressing one of the community’s most-requested deployment needs and making local inference easier.

Ready to run Hy-MT2-30B-A3B locally? Try the new GGUF relehuggingface.co/tencent/Hy-MT2…TVV7I
Explore Hy-MT2:
Hugginghuggingface.co/collections/te…McENW
Modelsmodelscope.cn/collections/Te…Yk9zQ
Gigithub.com/Tencent-Hunyua…Ac#TencentHye#HyMT2H#OpenSourceource

💬7🔄21❤️260👀17830📊53

join us,make different🥳

Tencent Hy (@TencentHunyuan) — Fri, 31 Jul 2026 02:01:37 GMT

join us,make different🥳

Shunyu Yao@ShunyuYao12

Hy ai4s is hiring :)

💬5🔄0❤️151👀29989📊19

For a finite set of integers (A), how much faster can (|A+A|) grow than (|A-A|)? A 1969 theorem gav...

Tencent Hy (@TencentHunyuan) — Thu, 30 Jul 2026 02:33:16 GMT

For a finite set of integers (A), how much faster can (|A+A|) grow than (|A-A|)?

A 1969 theorem gave an upper bound of 2 for the exponent. For more than 50 years, the best constructions barely exceeded 1.1.

With help from our research agent Hyra and the Hy3 model, we found an explicit construction showing that the optimal exponent is exactly 2.

A 50-year-old problem, solved.

Paper: arxiv.org/abs/2607.27199
Hyra blog: hy.tencent.ai/research/hyra
Formal proof: github.com/linhaowei1/sum…

💬40🔄193❤️1600👀381610📊377

🚀 We’ve open-sourced AngelSpec, an end-to-end speculative decoding framework supporting both train...

Tencent Hy (@TencentHunyuan) — Wed, 29 Jul 2026 12:43:55 GMT

🚀 We’ve  open-sourced AngelSpec, an end-to-end speculative decoding framework supporting both training and deployment.

On Hy3-A21B, DFly delivers a 1.98–2.40× end-to-end speedup over autoregressive decoding across tested concurrency levels from 4 to 64, with 10.5–11.8% higher throughput than DFlash.

Training code and Hy3-A21B MTP/DFly drafter weights are now available:
GitHub:github.com/Tencent/AngelS…Y
Paper:arxiv.org/abs/2607.25852v
Docs:angelspec.readthedocs.ioR
Hugging Face:huggingface.co/collections/An…C
ModelScope:modelscope.cn/collections/An…Y#Hy33#AngelSpecc#OpenSourcee

💬19🔄100❤️659👀43201📊182

Test Hy3 in GO. 💗

Tencent Hy (@TencentHunyuan) — Thu, 23 Jul 2026 03:05:26 GMT

Test Hy3 in GO.  💗

OpenCode@opencode

Hy3 now available in Go

text · 256K context

latest model from Tencent

💬16🔄5❤️443👀28213📊54

Agent & Coding 🔥🔥🔥

Tencent Hy (@TencentHunyuan) — Wed, 22 Jul 2026 08:29:23 GMT

Agent & Coding 🔥🔥🔥

Arena.ai@arena

Hy3 by Tencent is #5 in Agent Arena for open-weight models (#25 overall)! It also ranks as the #2 open model in the Frontend Code Arena (#16 overall)!

In Agent Arena: Hy3 lands at #25 overall (net -2.2%). Hy3 has strengths in tool-use (recovering well from CLI/bash errors, +2.6% and #25), its biggest weakness is steerability as it struggles to course-correct when users push back, coming in at -7.1% (#30).

Agent Arena measures models on millions of real-world, long-horizon agentic tasks. Models get web search, filesystem, and terminal tools to complete complex workflows: writing code, creating slide decks, researching the web, building apps, and analyzing documents.

We use causal tracing methodology to measure a model's net improvement, which indicates how much it improves outcomes relative to the average model.

Below we break down how Hy3 scored across 5 key signals, drawn from tasks submitted by a global community of users. Here’s an overview on the signals:

User-satisfaction proxies
- Confirmed Success: an explicit "yes that worked" feedback from the user
- Praise vs. Complaint: implicit sentiment in users reactions
- Steerability: can the model course-correct when you push back?

Tool-use proxies
- Bash Recovery: how it recovers from CLI errors (primary signal for tool use)
- Tool Hallucination: does it call tools that don't exist

Congrats to the @TencentHunyuan team on this release!

💬9🔄11❤️212👀22623📊31

Introducing Hyra-1.0, the first version of Hunyuan Research Agent. 💡💡💡 Built to recursively impr...

Tencent Hy (@TencentHunyuan) — Tue, 21 Jul 2026 04:02:41 GMT

Introducing Hyra-1.0, the first version of Hunyuan Research Agent. 💡💡💡

Built to recursively improve solutions for performance-driven research and engineering tasks.

Explore our demos in AI4AI, AI4Science, and AI4Fuhy.tencent.com/research/hyra8XN

💬21🔄94❤️876👀442907📊231

Can't Find Benchmark and download link ? See here 👇https://t.co/2bYLI8HRus

Tencent Hy (@TencentHunyuan) — Wed, 15 Jul 2026 03:57:16 GMT

Can't Find Benchmark and download link ? See here �huggingface.co/AngelSlim/Hy3-…s

Tencent Hy@TencentHunyuan

We’ve just released the 1-bit & 4-bit version of Hy3, a flagship-scale 295B model that can be served on a single GPU. 👌

Run Hy3 with llama.cpp, enable MTP, and experience powerful intelligence on dramatically lower hardware.🚀🚀🚀

Can’t wait to see what you buil#Hy3##Hy#GGUFG#llamacppacpp

💬7🔄4❤️86👀24618📊18

That Hy3 test from Jen @jenzhuscott was really impressive. Thank you. 🥰

Tencent Hy (@TencentHunyuan) — Wed, 15 Jul 2026 02:57:00 GMT

That Hy3 test from Jen @jenzhuscott was really impressive. Thank you. 🥰

Jen Zhu@jenzhuscott

Been power testing @TencentHunyuan Hy3 & not surprised why it’s the most used model on @OpenRouter (6 trn tokens) - remember the beautiful “Everything child learn” interactive site? I fed the underlying data to my Hermes X Hy3 agent - within 3 prompts made it into a gorgeous app - tiny model but very powerful! @ShunyuYao12 is a leader to watch closely 

(Links below) @TencentAI_News

Your browser does not support the video tag.

💬2🔄3❤️48👀10547📊8

We’ve just released the 1-bit & 4-bit version of Hy3, a flagship-scale 295B model that can be served...

Tencent Hy (@TencentHunyuan) — Tue, 14 Jul 2026 08:53:06 GMT

We’ve just released the 1-bit & 4-bit version of Hy3, a flagship-scale 295B model that can be served on a single GPU. 👌

Run Hy3 with llama.cpp, enable MTP, and experience powerful intelligence on dramatically lower hardware.🚀🚀🚀

Can’t wait to see what you buil#Hy3##Hy#GGUFG#llamacppacpp

Tencent Hy@TencentHunyuan

🚀Hy3 is here.

295B MoE. Best in its size class. Rivals trillion-scale flagships.
Reliable and affordable for most agentic usecases. 
Apache 2.0. Friendly for commercial use.
FREE API for 2 weeks →openrouter.ai/tencent/hy3:fr…i

�huggingface.co/tencent/Hy3SL
hy.tencent.com/research/hy3cW4

💬75🔄174❤️1555👀406944📊366

Hy3 has just claimed #1 on the OpenRouter LLM leaderboard! 🥇 Huge thanks to our partners for their...

Tencent Hy (@TencentHunyuan) — Mon, 13 Jul 2026 02:53:33 GMT

Hy3 has just claimed #1 on the OpenRouter LLM leaderboard! 🥇

Huge thanks to our partners for their hardcore support — this milestone wouldn’t be possible without you.

Fellow geeks and devs, jump in, test it out, and drop your feedback & reviews. 📷#H#Hy3O#OpenRouterA#AILLM

Tencent Hy@TencentHunyuan

🚀Hy3 is here.

295B MoE. Best in its size class. Rivals trillion-scale flagships.
Reliable and affordable for most agentic usecases. 
Apache 2.0. Friendly for commercial use.
FREE API for 2 weeks →openrouter.ai/tencent/hy3:fr…i

�huggingface.co/tencent/Hy3SL
hy.tencent.com/research/hy3cW4

💬75🔄52❤️687👀82398📊156

Check out how this gus uses Hy3 to generate such a beautiful data analysis report. Hy3 is performing...

Tencent Hy (@TencentHunyuan) — Fri, 10 Jul 2026 09:22:03 GMT

Check out how this gus uses Hy3 to generate such a beautiful data analysis report. Hy3 is performing amazingly!

x.com/kimmonismus/st…

Chubby♨️@kimmonismus

Tencent's Hy3 lands today with real coding and agent ability and a price that undercuts the models you'd put it against.

It's a 295B MoE with only 21B active parameters, a big part of why it stays cheap to serve, plus a 256K context window and an Apache 2.0 license that even outperforms GLM-5.1 although GLM is 2.5x larger.

On OpenRouter it runs at $0.14 per million input tokens and $0.58 per million output. For a model Tencent benchmarks against much larger flagships, that pricing is insane. Price-performance-ratio is China's real moat.

I already wrote about Tencent Hy3 earlier and the significant leap in quality it represents. Therefore, I'm pleased to recommend this model from @TencentHunyuan.

Open Router link down below:
#Hy3#Hunyuan#AICoding

Your browser does not support the video tag.

💬3🔄0❤️20👀5474📊5

Hy3 is now live on Hermes, Kilo Code, OpenCode, OpenClaw & Cline 🚀 Free to use. Plug in and pl...

Tencent Hy (@TencentHunyuan) — Thu, 09 Jul 2026 07:24:45 GMT

Hy3 is now live on Hermes, Kilo Code, OpenCode, OpenClaw & Cline 🚀

Free to use. Plug in and play.

Give it a spin and tell us what you think 👇

💬7🔄1❤️40👀6278📊14

Try it in @openclaw

Tencent Hy (@TencentHunyuan) — Thu, 09 Jul 2026 06:55:34 GMT

Try it in @openclaw

OpenClaw🦞@openclaw

Tencent Hy3 from @TencentHunyuan is free on @OpenRouter through July 21.

295B MoE, 256K context, built for coding, reasoning, agents and reliable tool use.

Try it in OpenClaw today: openclaw models set openrouter/tencent/hy3:free

💬3🔄4❤️97👀10571📊14

Thank you @SiliconFlowAI for support. 🫶

Tencent Hy (@TencentHunyuan) — Tue, 07 Jul 2026 15:03:18 GMT

Thank you @SiliconFlowAI for support. 🫶

SiliconFlow@SiliconFlowAI

🎁 Free Access for First 2 Weeks
Meet @TencentHunyuan Hy3
Now with T+0 support on SiliconFlow 🎉

Hy3: 295B MoE / 21B active / 262K context
✅ Refined iteratively through 50+ real business scenarios
✅ Cuts hallucinations & knowledge errors in half
✅ Stays on-intent over long-horizon tasks
✅ Stable agent execution with more tool-call wins, no infinite loops

Put it to real work through SiliconFlow ⬇️

💬6🔄1❤️127👀13017📊18

Hy3 is a real productivity booster. 🚀See how it handles these two workflows.

Tencent Hy (@TencentHunyuan) — Tue, 07 Jul 2026 08:04:00 GMT

Hy3 is a real productivity booster. 🚀See how it handles these two workflows.

Your browser does not support the video tag.

Your browser does not support the video tag.

💬3🔄1❤️48👀13031📊10

Thank you @ModelScope2022

Tencent Hy (@TencentHunyuan) — Tue, 07 Jul 2026 04:09:13 GMT

Thank you @ModelScope2022

ModelScope@ModelScope2022

Meet Hy3 on ModelScope! 
295B total / 21B active MoE, built for agentic workflows with 256K context and an FP8 variant ready for deployment. 🚀 License: Apache 2.0.
modelscope.ai/collections/Te…BP

🏆 Human eval: 270 experts compared outputs in blind real-world workflow tests. Hy3 scores 2.67/4, ahead of GLM-5.1 at 2.51/4, with the clearest gains in frontend development, CI/CD, and data & storage.

🛠️ Agent reliability: stronger tool calling, formatting, and error recovery, with SWE-Bench Verified variance within 4% across major scaffolds.

🧠 Multi-turn gains: issue rate drops from 17.4% to 7.9%, and MRCR rises from 42.9% to 75.1%.

⚙️ Model lineup: Hy3 BF16 instruct model plus Hy3-FP8 quantized instruct model, with vLLM and SGLang deployment support.

💬1🔄1❤️84👀9974📊9

Thanks to @vllm_project for supporting Hy3! Let's play with it.

Tencent Hy (@TencentHunyuan) — Tue, 07 Jul 2026 04:05:55 GMT

Thanks to @vllm_project for supporting Hy3! Let's play with it​.

vLLM@vllm_project

Spin it up now! 🚀

💬8🔄3❤️107👀11272📊18

Thank you @novita_labs for making Hy3 available on @OpenRouter 🎉🎉🎉

Tencent Hy (@TencentHunyuan) — Tue, 07 Jul 2026 03:00:47 GMT

Thank you @novita_labs for making Hy3 available on
@OpenRouter  🎉🎉🎉

Novita AI@novita_labs

⚡ Launching as a Day-0 partner: @TencentHunyuan Hy3 is now available on @OpenRouter.

🎉 Free through July 21.

Built for real-world business scenarios, Hy3 delivers:
🧠 295B MoE (21B active)
📚 Native 256K context
⚙️ Three configurable reasoning modes
💻 Strong coding, reasoning & long-context capabilities
🤖 Optimized for agentic workflows

Designed for productivity and real-world AI workflows, balancing reliability, efficiency, and cost at production sca#Hy3#LLM#Agentsgents

Your browser does not support the video tag.

💬4🔄6❤️95👀11434📊15

Great to have Hy3 available in @kilocode. Excited to see what developers build with it!

Tencent Hy (@TencentHunyuan) — Mon, 06 Jul 2026 23:52:25 GMT

Great to have Hy3 available in @kilocode. Excited to see what developers build with it!

Kilo@kilocode

Free in Kilo right now btw 👀

💬5🔄1❤️72👀8440📊12

🚀Hy3 is here. 295B MoE. Best in its size class. Rivals trillion-scale flagships. Reliable and affo...

Tencent Hy (@TencentHunyuan) — Mon, 06 Jul 2026 15:06:57 GMT

🚀Hy3 is here.

295B MoE. Best in its size class. Rivals trillion-scale flagships.
Reliable and affordable for most agentic usecases. 
Apache 2.0. Friendly for commercial use.
FREE API for 2 weeks →openrouter.ai/tencent/hy3:fr…i

�huggingface.co/tencent/Hy3SL
hy.tencent.com/research/hy3cW4

💬192🔄392❤️2913👀1204936📊929

12 Chinese AI models made their World Cup predictions. ⚽ The World Cup Round of 32 lineup is out....

Tencent Hy (@TencentHunyuan) — Mon, 29 Jun 2026 07:17:57 GMT

12 Chinese AI models made their World Cup predictions. ⚽ 

The World Cup Round of 32 lineup is out.🔥
The first leaderboard is in.👇

Tencent Hy went 29/32, ranking #1 among the 12 models after the Round of 32 was set.

Now comes the harder test:
whose predictions survive the knockout stage?#TencentHunyuana#AIA#WorldCupup

💬5🔄7❤️35👀5789📊12

1、Most RL stacks are built for one modality. UniRL applies a single post-training loop — generate → ...

Tencent Hy (@TencentHunyuan) — Tue, 09 Jun 2026 12:03:32 GMT

1、Most RL stacks are built for one modality. UniRL applies a single post-training loop — generate → score → advantage → update → sync — across model families. Model and algorithm are two independent axes, so your coverage is the model × algorithm product, not a fixed recipe menu.

2、One loop, every modality: text→image, text/image→video, vision-language, text-only LLM and VLM, the LLM→diffusion prompt-enhancer, and unified autoregressive+diffusion generation (Hunyuan-Image 3 and Bagel) — a model class no single-purpose RL repo can even express.

3、Built to scale: pluggable rollout engines (train-side / SGLang / vLLM-Omni) behind one typed contract, FSDP2 sharding, and three deployment modes from a single config knob.

4、Two team-original algorithms headline the release:

FlowDPPO: Policy optimization for flow/diffusion models with trust-region masks based on exact divergence (See our paper: Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models github.com/Tencent-Hunyua…)

DRPO: LLM RL with a smooth, advantage-weighted quadratic regularizer
(See our paper: Rethinking the Divergence Regularization in LLM RL [arxiv.org/abs/2606.09821])

💬1🔄1❤️14👀5564📊4

🚀Introducing UniRL, an RL infra for unified multimodal models. Together with two new RL algorithms:...

Tencent Hy (@TencentHunyuan) — Tue, 09 Jun 2026 12:03:23 GMT

🚀Introducing UniRL, an RL infra for unified multimodal models. Together with two new RL algorithms: DRPO and Flow-DPPO.

One RL loop across diffusion/flow matching models, LLMs/VLMs, and unified multimodal models👇

Codegithub.com/Tencent-Hunyua…c8

(yes — U(you)-ni-(need) RL 😉)

💬8🔄26❤️170👀31603📊48

Can AI truly edit audio, not just generate it? 🎧 Tencent Hy, in collaboration with SJTU, SII, NTU,...

Tencent Hy (@TencentHunyuan) — Mon, 08 Jun 2026 05:54:42 GMT

Can AI truly edit audio, not just generate it? 🎧

Tencent Hy, in collaboration with SJTU, SII, NTU, TJU, ZODA, PKU, FDU, and other collaborators, introduces MMAE.

MMAE--A Massive Multitask Audio Editing Benchmark, is the first comprehensive evaluation benchmark for speech and audio "Banana🍌"

Instead of simply requiring the AI to "generate" audio, it demands that the AI understand an existing audio clip and precisely modify it according to natural language instructions—altering what needs to be changed while leaving the rest untouched.

Current models show an Exact Match Rate (EMR) below 5%, revealing a major gap in reliable audio editing.

MMAE includes:
✅ 2,000 high-fidelity samples from real-world scenarios
✅ 17,741 fine-grained rubric evaluation items
✅ 7 modality settings across sound, music, speech and their mixtures
✅ 6 task complexity from basic modifications to multi-hop reasoning and multi-round editing
✅ 8 operation types across local and global granularities

How to use:
arXivarxiv.org/abs/2606.07229PZ
GitHub:github.com/ddlBoJack/MMAEMD
HuggingFacehuggingface.co/datasets/BoJac…Jn
Demoyoutu.be/6At5nTWhlXIk8

Your browser does not support the video tag.

💬9🔄39❤️253👀21013📊75

Planning is where LLMs move from “saying” to “doing.” Tencent Hy, in collaboration with the Gaoling...

Tencent Hy (@TencentHunyuan) — Fri, 05 Jun 2026 07:46:08 GMT

Planning is where LLMs move from “saying” to “doing.”

Tencent Hy, in collaboration with the Gaoling School of Artificial Intelligence at Renmin University of China, is excited to open-source PlanningBench - a scalable, verifiable framework for evaluating and training LLM planning capabilities.

With PlanningBench, you get:

✅ 30+ real-world planning tasks
✅ Automated verification
✅ Evaluation and training support

See how top-tier LLMs perform on PlanningBench 👇

Resources:
arXiv:arxiv.org/abs/2605.20873R
GitHub:github.com/Tencent-Hunyua…B
HuggingFace:huggingface.co/datasets/tence…x
#PlanningBenchh#TencentHunyuann#OpenSourcee 📷

💬6🔄15❤️88👀11684📊31

🚀We’re excited to officially release Hy-Memory — a powerful memory plugin built specifically for lo...

Tencent Hy (@TencentHunyuan) — Mon, 01 Jun 2026 09:01:25 GMT

🚀We’re excited to officially release Hy-Memory — a powerful memory plugin built specifically for long-term collaborative Agents like OpenClaw.

More than a retrieval tool, it becomes your Agent’s true “Second Brain.”

Powered by a 6-layer memory framework × System1/System2 dual system × three-layer evolutionary chain, Hy-Memory lets Agents remember durably, accurately, lightly, and understand you better.

➡️Solves memory fragmentation 
➡️70%+ fewer memories 
➡️45%+ higher info density per memory 
➡️35% less token usage on ultra-long contexts 
➡️20% faster memory updates.

Upgrade your Agent’s memory today!

📷Project & Downloadmemory.hunyuan.tencent.comGr
📷 OpenClaw Docmemory.hunyuan.tencent.com/openclaw/Ga8

💬44🔄81❤️943👀59996📊313

🚀 Open-source upgrade unlocked. Tencent Hy-MT2 is now under Apache License 2.0 — maximum freedom f...

Tencent Hy (@TencentHunyuan) — Tue, 26 May 2026 12:27:12 GMT

🚀 Open-source upgrade unlocked.

Tencent Hy-MT2 is now under Apache License 2.0 — maximum freedom for research, commercial use, fine-tuning, and derivatives. 

No strings attached.😎😎😎

Proud to push model weights back to the community. Our two variants are currently sitting at #1 and #4 on the Hugging Face trending leaderboard.

Clone, fork, break things, ship feedback. The iteration loop is live.🔥

Let’s keep building the frontier togeth#Tencentn#Hyt#HyMT2H#Apache2a#HuggingFaceg#OpenSourceAurceA

💬20🔄64❤️611👀33331📊139

🙏 Thank you all for the incredible love and support! Our latest Tencent Hunyuan translation mode...

Tencent Hy (@TencentHunyuan) — Tue, 26 May 2026 02:50:44 GMT

🙏 Thank you all for the incredible love and support!  

Our latest Tencent Hunyuan translation models are on fire on Hugging Face:  
🥰Hy-MT2-1.8B ranks #1
🥰Hy-MT2-30B-A3B ranks #4 on the open-source model trending leaderboard, with over 7K downloads already! 

To make it even easier for everyone, we’ve launched the Tencent Hy Translation WeChat mini-program, built on Hy-MT2. 

It supports voice input and offline translation, plus powerful customization of translation styles and instructions — delivering results that better match your expectations and feel far more practical.  

Try it out and share your feedback with us — we’d love to hear from you! 

Models on Hhuggingface.co/tencent/Hy-MT2…Ahuggingface.co/tencent/Hy-MT2…wB2 

GitHugithub.com/Tencent-Hunyua…jOX#HyMT2M#TencentHunyuanu#OpenSourcerce

💬22🔄34❤️332👀36077📊83

One More Thing. We are thrilled to announce that Tencent Hy is officially collaborating with the...

Tencent Hy (@TencentHunyuan) — Fri, 22 May 2026 03:10:15 GMT

One More Thing.  

 We are thrilled to announce that Tencent Hy is officially collaborating with the WMT26 organizers on the Preliminary Video Subtitle Translation Competition!  

 👉Join here:www2.statmt.org/wmt26/video-su…V 

Powered by our advanced Hy-MT series models, you can also take part in the General Machine Translation Competition.  

📷 Join herewww2.statmt.org/wmt26/translat…py 

Top participants have the chance to win special grand prizes!  We warmly invite researchers, developers, AI enthusiasts, and everyone passionate about machine translation to join us.   

Together, let’s push the boundaries of AI and drive the future of machine translation technology forward!   

Don’t miss this incredible opportunity — register and participate today!#WMT262#HyH#MachineTranslationo#AIInnovationWeWe look forward to seeing your submissions!

💬0🔄3❤️18👀3491📊4

🚀 Introduce Hy-MT2: New Open-Source Multilingual Translation Model We proudly launch our new Hy-MT...

Tencent Hy (@TencentHunyuan) — Thu, 21 May 2026 08:52:32 GMT

🚀 Introduce Hy-MT2: New Open-Source Multilingual Translation Model

We proudly launch our new Hy-MT2 translation model and the Tencent Hy Translation mini-program!

Hy-MT2 is a powerful multilingual model supporting seamless translation across 33 languages — and it's fully open-source!

It's 7B and 30B-A3B models achieve state-of-the-art performance among all open-source models on various translation tasks, surpassing models with dozens of times more parameters.

The lightweight 1.8B model even outperforms mainstream commercial APIs like Microsoft and so on. Powered by Tencent AngelSlim 1.25-bit extreme quantization, it needs just 440MB storage and enables effortless local inference on mainstream mobile chips — with 1.5x faster speed vs. Hy-MT1.5.

Open-source AI translation just got way smarter, faster, and more accessible! 🌏

Project Pageaistudio.tencent.com/llm/zh?tabInde…jB
Hugging Facehuggingface.co/collections/te…Du
Modelscopemodelscope.cn/collections/Te…po
Githubgithub.com/Tencent-Hunyua…OX

💬20🔄80❤️529👀79003📊158

🎉 🎉 🎉 We're open-sourcing Chronicles-OCR, a visual perception benchmark evaluating VLLMs on ancie...

Tencent Hy (@TencentHunyuan) — Tue, 19 May 2026 02:46:26 GMT

🎉 🎉 🎉 We're open-sourcing Chronicles-OCR, a visual perception benchmark evaluating VLLMs on ancient Chinese characters.

The dataset spans 3,000 years of evolution. It covers 7 historical scripts from Oracle Bone to Cursive, featuring 2,800 balanced images across highly diverse physical media.

We assess models on 4 core tasks: 

• Character Spotting 
• Fine-grained Recognition 
• Ancient Text Parsing
 • Script Classification

The evaluation reveals how visual distribution shifts affect model perception over time. 

Explore the dataset and paper below. 👇

📄 Paarxiv.org/abs/2605.11960Rp4OQ 
🔗 Gigithub.com/VirtualLUOUCAS…6mjBRJ

💬2🔄31❤️157👀17925📊41

Hy3 preview is now on @gmi_cloud. 🙌

Tencent Hy (@TencentHunyuan) — Wed, 13 May 2026 03:27:17 GMT

Hy3 preview is now on @gmi_cloud. 🙌

GMI Cloud@gmi_cloud

Hy3 preview from @TencentHunyuan is now live on GMI 

#1 on OpenRouter's LLM leaderboard, open-sourced, and the strongest model in the Hy series.

It excels at at complex reasoning and STEM, coding and agent workflows, long-context tasks (256K), and natural, emphathetic chat.

295B MoE · 21B active · open weights. 

Try it now 👇

💬1🔄1❤️35👀6351📊5

Hy3 preview handles complex agentic tasks. See for yourself. 👇

Tencent Hy (@TencentHunyuan) — Mon, 11 May 2026 09:38:21 GMT

Hy3 preview handles complex agentic tasks. See for yourself. 👇

Python Space@python_spaces

Got early access to Tencent's Hy3 preview.

This is the strongest model in the Hy series. Built on rebuilt pre-training and reinforcement-learning infrastructure.

I tested its agentic capabilities. Results?

It's built for real-world effectiveness, not just benchmark scores.

256K context length. Fast-and-slow-thinking fused MoE architecture. Cost-effective at scale.

@TencentHunyuan#Hy3preview#Tencent

Test case below: 👇

Your browser does not support the video tag.

💬4🔄4❤️51👀6875📊10

The free period on @OpenRouter has ended. During these two weeks, Hy3 preview reached: #1 in overa...

Tencent Hy (@TencentHunyuan) — Sat, 09 May 2026 11:25:01 GMT

The free period on @OpenRouter has ended.

During these two weeks, Hy3 preview reached: 
#1 in overall token usage 
#1 in coding 
#1 in tool calls 
15.4% market share across all providers

Hy3 preview remains available on OpenRouter at competitive pricing. Keep building — and keep the feedback coming.

openrouter.ai/tencent/hy3-pr…

💬7🔄10❤️163👀10536📊31

Hy3 preview's token usage has grown 10x compared to our previous generation Hy2, with coding and age...

Tencent Hy (@TencentHunyuan) — Thu, 07 May 2026 02:30:54 GMT

Hy3 preview's token usage has grown 10x compared to our previous generation Hy2, with coding and agent workloads driving the growth.

Within Tencent's own products, WorkBuddy, CodeBuddy, and QClaw saw over 16.5x growth in token usage.

💬12🔄5❤️94👀12643📊26

Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens pro...

Tencent Hy (@TencentHunyuan) — Wed, 06 May 2026 10:53:05 GMT

Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week.

#1 in overall usage, tool calls, and coding. 15.4% market share across all providers.🏆

Top apps running Hy3 preview: Hermes Agent, Claude Code, Kilo Code, OpenClaw, Cline.@NousResearch@claudeai@kilocodehq@openclaw@cline 

Huge thanks to every developer building with it. 🙏

Try it on OpenRouteropenrouter.ai/tencent/hy3-pr…Vk

💬12🔄28❤️231👀27597📊55

We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on you...

Tencent Hy (@TencentHunyuan) — Wed, 29 Apr 2026 13:55:43 GMT

We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate.

At 1.8B parameters, it matches commercial translation APIs and 235B-scale models on standard benchmarks. By quantizing to 1.25-bit, memory drops from 3.3GB (FP16) to 440MB — 25% smaller and ~10% faster than prior 1.67-bit approaches, with no accuracy loss.

Covers 33 languages, 5 dialects, and 1,056 translation directions including minority languages like Tibetan and Mongolian.

Our translation model has won 30 first-place rankings in international MT competitions and is already deployed across multiple Tencent products.🏆

📲Demo APK (Android)huggingface.co/AngelSlim/Hy-M…vw
🤗Hugging Facehuggingface.co/AngelSlim/Hy-M…z4L
🔗GitHgithub.com/tencent/AngelS…Delf
📄Paarxiv.org/abs/2601.07892pNrnt

💬60🔄277❤️2196👀140143📊671

Excited to see Hy3 preview live on @arena. Try it out and let us know what you think!

Tencent Hy (@TencentHunyuan) — Sat, 25 Apr 2026 03:57:52 GMT

Excited to see Hy3 preview live on @arena. Try it out and let us know what you think!

Arena.ai@arena

Hy3 preview (295B A21B) an open source model by @TencentHunyuan is now live on Arena.

Evaluate it across Text & Code Arena in Battle mode. Scores incoming soon.

💬4🔄4❤️75👀20475📊12

Now live on @opencode and free for 2 weeks👏

Tencent Hy (@TencentHunyuan) — Thu, 23 Apr 2026 17:05:46 GMT

Now live on @opencode and free for 2 weeks👏

OpenCode@opencode

OpenCode x Tencent Hy3 preview — free for 2 weeks

Strongest in the Hy series
- 256K context · reasoning · text only
- 295B (A21B)
- ☝️means it's built for strong performance at lower token cost; ur welcome

💬1🔄4❤️54👀6988📊8

Hy3 preview is now available on @OpenRouter. Try it now for free through May 8th!

Tencent Hy (@TencentHunyuan) — Thu, 23 Apr 2026 17:02:34 GMT

Hy3 preview is now available on @OpenRouter. Try it now for free through May 8th!

OpenRouter@OpenRouter

The new Hy3-Preview model from @TencentHunyuan is live for free on OpenRouter!

It’s a 295B MoE model (21B active) with controllable reasoning effort.
A cost-effective, practical model that performs strongly in coding agents and delivers comprehensive general capabilities.

💬0🔄4❤️43👀4770📊6

We're now live on @openclaw

Tencent Hy (@TencentHunyuan) — Thu, 23 Apr 2026 17:00:07 GMT

We're now live on @openclaw

OpenClaw🦞@openclaw

OpenClaw 2026.4.22 🦞

🧠 Tencent Hy3 joins the model list
🖼️ Grok image + voice tools
🧰 Local TUI + /models add
📦 Auto-install plugins + diagnostics export

Big release, tiny release notes... kiddgithub.com/openclaw/openc…taNlv

💬1🔄2❤️31👀4149📊5

Hy3 preview is now available on OpenRouter. Try it now for free through May 8th: https://t.co/wAC9GO...

Tencent Hy (@TencentHunyuan) — Thu, 23 Apr 2026 16:52:23 GMT

Hy3 preview is now available on OpenRouter. Try it now for free through May 8th: openrouter.ai/tencent/hy3-pr…

💬1🔄7❤️59👀10506📊9

Big thanks to @lmsysorg🙌Try it now with SGLang!

Tencent Hy (@TencentHunyuan) — Thu, 23 Apr 2026 16:46:14 GMT

Big thanks to @lmsysorg🙌Try it now with SGLang!

LMSYS Org@lmsysorg

🎉 Meet Hy3 preview from @TencentHunyuan , a 295B hybrid MoE (21B active) with 256K context. Day-0 support is now live in SGLang!
→ Strong reasoning: top results on FrontierScience-Olympiad, IMO-AnswerBench & GPQA Diamond
→ 256K context: big gains on CL-bench & LongBench v2
→ Code & agents: competitive on SWE-Bench Verified, Terminal-Bench 2.0 & BrowseComp
→ Co-designed with Yuanbao for sharper intent & natural replies

📖 Cookbookdocs.sglang.io/cookbook/autor…zI
Try it now with SGLang!

💬0🔄2❤️24👀4043📊3