Tencent Hy(@TXhunyuan)

Much more AI coming ❤️

Tencent Hy (@TencentHunyuan) — Fri, 11 Sep 2026 02:58:11 GMT

Much more  AI coming ❤️

Ivan Fioravanti ᯅ@ivanfioravanti

This morning I visited Tencent HQ in Beijing!
A marvelous office, from the architecture to the amazing showroom where I've really understood values and services offered by Tencent. 

Thanks to the @TencentHunyuan team in Beijing for the amazing lunch talking about hybrid AI scenarios and more! 

Hy4 Preview is just the tip of the iceberg, there is much more to come! @TencentAI_news Can't wait to see and try what you'll deliver in the near future 🚀

🔗 View Quoted Tweet

💬6🔄1❤️76👀6863📊12

⚡ Powered by xgo.ing

🚀 AuK is officially here. Nano banana🍌 for audio An open-source foundation model for unified spee...

Tencent Hy (@TencentHunyuan) — Thu, 10 Sep 2026 10:33:40 GMT

🚀 AuK is officially here. Nano banana🍌 for audio

An open-source foundation model for unified speech generation and editing.
Natural-language instructions + reference audio. One interface.
Zero-shot TTS. Instruction-controlled generation. Content editing. Whisper-conversion. De-accent. Timbre/style/emotion edit. Speed/Pitch control. Enhancement, denoising, multi-speaker and music separation.
Also releasing AuK-Flash: 4-step inference. ~4.5× faster under matched conditions.
Code, weights, and demo are live. Try it and share your feedback.

🤗 Paper & upvothuggingface.co/papers/2609.08…JRF
⭐ GitHub & stagithub.com/Tencent-Hunyua…8Yv

Your browser does not support the video tag.

🔗 View on Twitter

💬38🔄103❤️924👀40479📊300

⚡ Powered by xgo.ing

✔️Hy4 preview just shipped an upgrade. You flagged it: long thinking + over-verification on complex ...

Tencent Hy (@TencentHunyuan) — Mon, 07 Sep 2026 09:52:10 GMT

✔️Hy4 preview just shipped an upgrade.
You flagged it: long thinking + over-verification on complex tasks.
We optimized it. Now live for everyone.
Same task quality. Fewer turns. Lower in/out tokens.
Bench + human eval both confirm.
We’ll keep iterating fast. Try it and tell us what still breaks.

Try on WorkBuddy: WorkBuddy.ai

Tencent Hy@TencentHunyuan

🚀 Hy4 preview is here.

770B, 49B active, 1M context.
Built for productivity.
Open source frontier.
Consistent affordable price.
Use it. Tell us what breaks.

More on Hy bloghy.tencent.ai/research/hy4-p…C
HuggingFacehuggingface.co/tencent/Hy4-pr…R
Githubgithub.com/Tencent-Hunyua…L

🔗 View Quoted Tweet

💬64🔄75❤️1197👀133942📊203

⚡ Powered by xgo.ing

One more thing about Hy4 preview that is particularly interesting. In AI research. Hy4 preview found...

Tencent Hy (@TencentHunyuan) — Tue, 01 Sep 2026 10:12:32 GMT

One more thing about Hy4 preview that is particularly interesting.
In AI research. Hy4 preview found inference bottlenecks on its own and lifted e2e throughput 31.8% via operator fusion and comms opts — stable across context lengths and concurrency.
MORE ON: hy.tencent.ai

Tencent Hy@TencentHunyuan

🚀 Hy4 preview is here.

770B, 49B active, 1M context.
Built for productivity.
Open source frontier.
Consistent affordable price.
Use it. Tell us what breaks.

More on Hy bloghy.tencent.ai/research/hy4-p…C
HuggingFacehuggingface.co/tencent/Hy4-pr…R
Githubgithub.com/Tencent-Hunyua…L

🔗 View Quoted Tweet

💬28🔄33❤️462👀36006📊83

⚡ Powered by xgo.ing

sooooo nice

Tencent Hy (@TencentHunyuan) — Mon, 31 Aug 2026 10:57:29 GMT

sooooo nice

苏打白.Dev@sodawhite_dev

我用腾讯的Hy4 preview做了一个《清明上河图》动画效果。

同样的提示词，效果吊打GLM5.3 -flash

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬10🔄5❤️164👀16008📊27

⚡ Powered by xgo.ing

Everyone can generate a SPIDER-MAN with Hy4 preview

Tencent Hy (@TencentHunyuan) — Mon, 31 Aug 2026 06:02:42 GMT

Everyone can generate a SPIDER-MAN with Hy4 preview

💬8🔄3❤️152👀13775📊28

⚡ Powered by xgo.ing

🤝

Tencent Hy (@TencentHunyuan) — Sat, 29 Aug 2026 16:08:02 GMT

🤝

ModelScope@ModelScope2022

Tencent HY open-sourced Hy4 preview: a flagship MoE with 1M context, and their biggest generational leap measured to date. Apache 2.0.🔥
�modelscope.cn/models/Tencent…AC

⚙️ 770B total params, 49B active per token. Ships with a native MTP layer for speculative decoding out of the box.
📊 Blind eval by 163 internal experts across 203 real engineering tasks: it edges out GLM 5.3 (avg 2.99 vs 2.92) and Kimi K3 (2.99 vs 2.94).
💼 Trained on real production workflows: software engineering, office and data analysis, game development, and scientific research.

🌍 For global usmodelscope.ai/models/Tencent…OFpfV

🔗 View Quoted Tweet

💬3🔄3❤️100👀10254📊12

⚡ Powered by xgo.ing

Hy4 preview runs in vLLM

Tencent Hy (@TencentHunyuan) — Sat, 29 Aug 2026 16:06:56 GMT

Hy4 preview runs in vLLM

vLLM@vllm_project

@TencentHunyuan's Hy4-preview runs in vLLM from day 0, verified on NVIDIA GPUs. 🎉

- 770B total, 49B active, 256 routed experts plus one shared
- 1M context, but each query attends to just 2048 tokens
- Only 21 of the 78 layers compute their own sparse index, the other 57 reuse one
- A 10B MTP layer ships inside the checkpoint, 0.7B of it active, draft depth 3

Tencent's HPC-Ops attention and MoE kernels have been in vLLM main since Hy3.

VLLM_ENABLE_HPC_OPS=1 vllm serve tencent/Hy4-preview-FP8 -tp 8

Thanks @TencentHunyuan for the preview weights! 🙌

recipes.vllm.ai/tencent/Hy4-pr…yZb

🔗 View Quoted Tweet

💬1🔄6❤️141👀14529📊15

⚡ Powered by xgo.ing

We compressed Hy4-preview from 1.5TB to ～200GiB GGUF and it still works well ! Meet MIX-STQ1_0.The...

Tencent Hy (@TencentHunyuan) — Sat, 29 Aug 2026 05:31:29 GMT

We compressed Hy4-preview from 1.5TB to ～200GiB GGUF and it still works well ! 

Meet MIX-STQ1_0.The trick isn’t just going low, it’s deciding where: calibration data picks each layer’s bit-width, some down to 1.31-bit STQ1_0, some up to 2.06-bit IQ2_XXS. Same budget, lower error. 

Accuracy barely moves vs BF16
📊 MCP Atlas 83.7→83.2
📊 SWE-Bench multi 82.9→81.3
📊 MRCR 81.3→81.1
📊 IFBench 73.5→72.5

See the details on HF :  AngelSlim/Hy4-preview-GGUF

Weights & low-bit GGUFhuggingface.co/AngelSlim/Hy4-…T9#LLM#Quantizationa#llamacppm#Hyp #Hy

Tencent Hy@TencentHunyuan

🚀 Hy4 preview is here.

770B, 49B active, 1M context.
Built for productivity.
Open source frontier.
Consistent affordable price.
Use it. Tell us what breaks.

More on Hy bloghy.tencent.ai/research/hy4-p…C
HuggingFacehuggingface.co/tencent/Hy4-pr…R
Githubgithub.com/Tencent-Hunyua…L

🔗 View Quoted Tweet

💬83🔄196❤️1842👀630573📊390

⚡ Powered by xgo.ing

Try Hy4 preview in Cline

Tencent Hy (@TencentHunyuan) — Sat, 29 Aug 2026 02:34:36 GMT

Try Hy4 preview in Cline

Cline@cline

Tencent Hy4 Preview leads on SWE-bench Pro. 770B, 49B active, 1M context, and their biggest generational leap measured to date.

It’s exciting to see another open weights model compete against the frontier.

Try in Cline with:
1. npm i -g cline
2. /model
3. Select Hy4 preview

🔗 View Quoted Tweet

💬5🔄6❤️205👀12865📊24

⚡ Powered by xgo.ing

Hy 4 preview, available in OpenCode Go 👏

Tencent Hy (@TencentHunyuan) — Sat, 29 Aug 2026 02:27:41 GMT

Hy 4 preview, available in OpenCode Go 👏

OpenCode@opencode

Hy4 preview is now available in OpenCode Go

770B/49B · 1M context · built for coding agents

🔗 View Quoted Tweet

💬8🔄6❤️254👀18557📊31

⚡ Powered by xgo.ing

Free for 2 weeks

Tencent Hy (@TencentHunyuan) — Fri, 28 Aug 2026 13:42:00 GMT

Free for 2 weeks

WorkBuddy@WorkBuddy_AI

Hy4 preview from @TencentHunyuan  is here—and it’s now available on WorkBuddy.

We tested it inside real agent workflows across research, Office tasks, frontend development, and game development.

A few highlights:

→ Strong performance on research tasks that require finding, organizing, and synthesizing information
→ More capable Office workflows, from cross-file analysis to Excel accuracy and PPT visual layout
→ Better frontend execution, with stronger visual quality and interaction design
→ More capable game development, including building playable prototypes from natural-language instructions

What stands out most is how well Hy4 preview fits into end-to-end agent workflows — not just answering questions, but actually completing multi-step productivity tasks.

Hy4 preview is FREE to use on WorkBuddy for the next 2 weeks.

And Hy3 will remain FREE through the end of September.

Try Hy4 preview on WorkBuddy with your own real-world tasks and see how it performs.

🔗 View Quoted Tweet

💬37🔄41❤️713👀45471📊140

⚡ Powered by xgo.ing

Keep going 💪

Tencent Hy (@TencentHunyuan) — Fri, 28 Aug 2026 08:23:17 GMT

Keep going 💪

Arena.ai@arena

Big news: Hy4 preview by @TencentHunyuan just landed ~#5 in the Code Arena: WebDev with 1633 pts (AutoEval).

This is a significant improvement from Hy3 at #31 overall (+115 pts)! Among open models, Hy4 preview is ~#3, compared to Hy3 at #7.

Note: this is an early AutoEval score, in which a Reward Model trained on Arena's human preference data casts automatic votes in place of live votes. We’ll continue to see how scores converge as more live human votes come in. See thread for more info on the methodology behind AutoEval.

Congrats to the @TencentHunyuan team on this release!

🔗 View Quoted Tweet

💬9🔄8❤️376👀21095📊44

⚡ Powered by xgo.ing

🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier....

Tencent Hy (@TencentHunyuan) — Fri, 28 Aug 2026 06:23:31 GMT

🚀 Hy4 preview is here.

770B, 49B active, 1M context.
Built for productivity.
Open source frontier.
Consistent affordable price.
Use it. Tell us what breaks.

More on Hy bloghy.tencent.ai/research/hy4-p…C
HuggingFacehuggingface.co/tencent/Hy4-pr…R
Githubgithub.com/Tencent-Hunyua…L

💬338🔄565❤️5393👀2822121📊1418

⚡ Powered by xgo.ing

Thank you. We’re working on it — more soon.

Tencent Hy (@TencentHunyuan) — Wed, 26 Aug 2026 06:54:09 GMT

Thank you. We’re working on it — more soon.

Jen Zhu@jenzhuscott

Tencent @TencentHunyuan - 

I’m ready for Hy4.  🚀

🔗 View Quoted Tweet

💬15🔄17❤️472👀52114📊60

⚡ Powered by xgo.ing

Hy Agent Harness For Video Generation.

Tencent Hy (@TencentHunyuan) — Fri, 21 Aug 2026 12:10:26 GMT

Hy Agent Harness For Video Generation.

Tianyu Pang@TianyuPang1

HyCreator: an agent harness for long video generation

🚀 End2end Auto Mode
⏲️ Generate 10-minute scale films with zero human intervention
👨‍🦰 Switch to real-time interactive editing whenever you want

Apply for early acceshycreator.tencent.comXLh

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬5🔄20❤️296👀34156📊59

⚡ Powered by xgo.ing

Our translation models are now on @OpenRouterAI 🌐 • Hy-MT2-1.8B • Hy-MT2-30B-A3B Built for real-w...

Tencent Hy (@TencentHunyuan) — Fri, 21 Aug 2026 08:03:54 GMT

Our translation models are now on @OpenRouterAI 🌐

• Hy-MT2-1.8B
• Hy-MT2-30B-A3B

Built for real-world translation across 33 languages, with strong multilingual instruction following for structured, contextual, and style-guided tasks.

Let’s try them out ↓openrouter.ai/tencentD

💬17🔄25❤️400👀25209📊90

⚡ Powered by xgo.ing

8x the normal usage on OpenCode👌

Tencent Hy (@TencentHunyuan) — Fri, 21 Aug 2026 02:54:16 GMT

8x the normal usage on OpenCode👌

OpenCode@opencode

Hy3 will get 8x the normal usage until August 30th

that's $480 of usage for $10

available to all OpenCode Go subscribers

🔗 View Quoted Tweet

💬13🔄1❤️365👀21723📊43

⚡ Powered by xgo.ing

Hyra keeps pushing the frontier. Since our last math update, four more advances have landed: 📐 3D B...

Tencent Hy (@TencentHunyuan) — Wed, 19 Aug 2026 09:06:37 GMT

Hyra keeps pushing the frontier.
Since our last math update, four more advances have landed:
📐 3D Blaschke–Lebesgue: raised the universal lower bound for constant-width bodies from 0.380799w³ → 0.411040w³ (now 97.9% of the conjectured Meissner optimum).
∫ Beurling–Ahlfors: improved the best uniform (L^p) coefficient from 1.575 → 1.523958, moving closer to Iwaniec’s conjectured sharp bound.
± Partial Hadamard matrices: extended asymptotic counting from the cubic scale down to the near-quadratic regime.
[,] Operator commutators: improved the cost of approximating the identity from Tao’s O(log⁵(1/ε)) to O(log³), narrowing the gap toward the known logarithmic lower bound.
We are making open-source models better at solving open problems!
Check the results:github.com/Tencent-Hunyua…U

💬5🔄8❤️147👀17899📊28

⚡ Powered by xgo.ing

📄New Research on Self-Evolving Agents: When AI agents modify themselves, how do we know they actual...

Tencent Hy (@TencentHunyuan) — Wed, 12 Aug 2026 07:42:34 GMT

📄New Research on Self-Evolving Agents:
When AI agents modify themselves, how do we know they actually got better?

We present Diving into Reliable Self-Evolving Agents: A Survey—a systematic map of how agents self-evolve and what evidence is needed to trust each update.
The survey:
🔹 Defines an L0–L4 taxonomy for self-evolving agents
🔹 Introduces a reliability ladder for trustworthy updates
🔹 Curates 549 works in an open companion catalog
One core principle: no update should control the only evidence used to accept itself.

Explore the full survey ↓
📄 Papopenreview.net/forum?id=CGO1h…dF2FP
🌐 Prowkqdzkd.github.io/Awesome-Reliab…9EIPf0
💻 Ggithub.com/wkqdzkd/Awesom…now4J9X

💬14🔄50❤️379👀24604📊120

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

💬80🔄262❤️2502👀233235📊832

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

🔗 View Quoted Tweet

💬5🔄3❤️124👀17284📊19

⚡ Powered by xgo.ing

🚀 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

💬32🔄57❤️399👀154063📊134

⚡ Powered by xgo.ing

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👀29859📊120

⚡ Powered by xgo.ing

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❤️261👀18551📊53

⚡ Powered by xgo.ing

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 :)

🔗 View Quoted Tweet

💬5🔄0❤️150👀30604📊19

⚡ Powered by xgo.ing

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🔄194❤️1593👀390887📊375

⚡ Powered by xgo.ing

🚀 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🔄101❤️658👀43965📊182

⚡ Powered by xgo.ing

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

🔗 View Quoted Tweet

💬16🔄5❤️440👀28639📊54

⚡ Powered by xgo.ing

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!

🔗 View Quoted Tweet

💬9🔄11❤️210👀23038📊30

⚡ Powered by xgo.ing

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❤️874👀443734📊231

⚡ Powered by xgo.ing

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

🔗 View Quoted Tweet

💬7🔄4❤️86👀24964📊18

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

🔗 View Quoted Tweet

💬2🔄3❤️48👀10985📊8

⚡ Powered by xgo.ing

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

🔗 View Quoted Tweet

💬74🔄173❤️1544👀409141📊362

⚡ Powered by xgo.ing

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

🔗 View Quoted Tweet

💬75🔄52❤️687👀82536📊156

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

🔗 View Quoted Tweet

💬3🔄0❤️21👀5543📊5

⚡ Powered by xgo.ing

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👀6306📊14

⚡ Powered by xgo.ing

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

🔗 View Quoted Tweet

💬3🔄4❤️97👀10571📊14

⚡ Powered by xgo.ing

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 ⬇️

🔗 View Quoted Tweet

💬6🔄1❤️127👀13017📊18

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄1❤️48👀13031📊10

⚡ Powered by xgo.ing

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.

🔗 View Quoted Tweet

💬1🔄1❤️84👀9974📊9

⚡ Powered by xgo.ing

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! 🚀

🔗 View Quoted Tweet

💬8🔄3❤️107👀11272📊18

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

🔗 View Quoted Tweet

💬4🔄6❤️95👀11434📊15

⚡ Powered by xgo.ing

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 👀

🔗 View Quoted Tweet

💬5🔄1❤️72👀8440📊12

⚡ Powered by xgo.ing

🚀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

💬191🔄392❤️2901👀1215320📊924

⚡ Powered by xgo.ing

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

⚡ Powered by xgo.ing

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

⚡ Powered by xgo.ing

🚀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

⚡ Powered by xgo.ing

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.

🔗 View on Twitter

💬9🔄39❤️253👀21013📊75

⚡ Powered by xgo.ing

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

Tencent Hy(@TXhunyuan)

Much more AI coming ❤️

🚀 AuK is officially here. Nano banana🍌 for audio An open-source foundation model for unified spee...

✔️Hy4 preview just shipped an upgrade. You flagged it: long thinking + over-verification on complex ...

One more thing about Hy4 preview that is particularly interesting. In AI research. Hy4 preview found...

sooooo nice

Everyone can generate a SPIDER-MAN with Hy4 preview

🤝

Hy4 preview runs in vLLM

We compressed Hy4-preview from 1.5TB to ～200GiB GGUF and it still works well ! Meet MIX-STQ1_0.The...

Try Hy4 preview in Cline

Hy 4 preview, available in OpenCode Go 👏

Free for 2 weeks

Keep going 💪

🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier....

Thank you. We’re working on it — more soon.

Hy Agent Harness For Video Generation.

Our translation models are now on @OpenRouterAI 🌐 • Hy-MT2-1.8B • Hy-MT2-30B-A3B Built for real-w...

8x the normal usage on OpenCode👌

Hyra keeps pushing the frontier. Since our last math update, four more advances have landed: 📐 3D B...

📄New Research on Self-Evolving Agents: When AI agents modify themselves, how do we know they actual...

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

3⃣3⃣3⃣

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

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

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

join us,make different🥳

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

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

Test Hy3 in GO. 💗

Agent & Coding 🔥🔥🔥

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

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

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

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

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

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

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

Try it in @openclaw

Thank you @SiliconFlowAI for support. 🫶

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

Thank you @ModelScope2022

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

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

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

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

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

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

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

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

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

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