Tencent Hy ✓
@TencentHunyuan · joined 10 Jul 2024
Tencent's foundation model for text, image, video, and 3D generation.
52 302Followers
8Following
780Posts total
3.8MViews on collected posts
Latest posts
Looking for new posts…
@TencentHunyuan Top! Will you update open weights too?
2.2K views · 18 likes
· 0 reposts · 0 replies
Open on X →
✔️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
126.9K views · 1.2K likes
· 75 reposts · 58 replies
Open on X →
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: https://t.co/ejONBL8E
34.2K views · 462 likes
· 32 reposts · 27 replies
Open on X →
@TencentHunyuan nobody was loading 1.5tb. the product was always whether 200gb still codes
2.3K views · 11 likes
· 0 reposts · 0 replies
Open on X →
@TencentHunyuan These are brilliant pieces of work, I’m amazed you haven’t caused a stir yet. There’s a serious level of political fanaticism in this community, the fanbase of certain models is dominating the community to an extreme degree, and this really bothers me. Well done,
5.3K views · 66 likes
· 0 reposts · 0 replies
Open on X →
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 https
614.2K views · 1.8K likes
· 197 reposts · 85 replies
Open on X →
@TencentHunyuan Is Tencent a big league player now? The benchmarks are incredible. Looks like gotta give it a try.
17.1K views · 55 likes
· 1 reposts · 1 replies
Open on X →
@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
23.3K views · 87 likes
· 5 reposts · 7 replies
Open on X →
@TencentHunyuan Shipping it live in @CommandCodeAI 🐐
Excited to be an early partner to benchmark Hy4 preview, in our internal bench it performed better than GLM 5.3 Flash on token costs and time. Will continue to test and share more results. https://t.co/at987HPwnT
10.3K views · 95 likes
· 4 reposts · 7 replies
Open on X →
@TencentHunyuan the honest answer is that most people don't know what to do with a 770b model, they just want something that works and doesn't break the bank
5.4K views · 30 likes
· 0 reposts · 1 replies
Open on X →
Tencent HY open-sourced Hy4 preview: a flagship MoE with 1M context, and their biggest generational leap measured to date. Apache 2.0.🔥
🤖 https://t.co/HriyFmGtK8
⚙️ 770B total params, 49B active per token. Ships with a native MTP layer for speculative decoding out of the box. ht
38.1K views · 211 likes
· 21 reposts · 7 replies
Open on X →
🚀 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 blog：https://t.co/rbl1IWRk3C
HuggingFace：https://t.co/mE9wevH5XR
Github：https://t.co/pyl9zckpoL https://t.co/4
2.8M views · 5.4K likes
· 567 reposts · 339 replies
Open on X →
Against accounts of the same size
18 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.
Median views12 146this account924median for 10K–100K
Reach, %23.22%this account3.62%median for 10K–100K
Engagement, %0.61%this account1.52%median for 10K–100K
| Metric | This account | Median for 10K–100K | Ratio |
|---|---|---|---|
| Median views per post | 12 146 | 924 | 13.2× |
| Reach (views ÷ followers) | 23.22% | 3.62% | 6.42× |
| Engagement rate | 0.61% | 1.52% | 0.40× |
Others in this range → Compare with another account → How these benchmarks are built →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
23.3K28 Aug
17.1K
614.2K29 Aug
2.6K
5.3K
2.3K
14K
9.5K
14.9K31 Aug
34.2K1 Sep
126.9K7 Sep
2.2K
2.2K
902
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.43%28 Aug
0.33%
0.36%29 Aug
0.38%
1.25%
0.48%
1.05%
1.09%
1.17%31 Aug
1.54%1 Sep
1.06%7 Sep
0.84%
0.18%
0.44%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes71.2%9 868 in total
Reposts6.6%917 in total
Replies3.9%546 in total
Quotes3.9%543 in total
Bookmarks14.3%1 977 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Similar accounts
IET 17 ✓
@Inevitably_17
104.6K followers
· 22.6K posts
Team4Nature
@Team4Nature
104.6K followers
· 142.7K posts
Vincent Bevins
@Vinncent
104.6K followers
· 60.2K posts
Luke Dashjr ✓
@LukeDashjr
104.6K followers
· 162.2K posts
Polling Canada ✓
@CanadianPolling
104.6K followers
· 26.1K posts
North American Aerospace Defense Command ✓
@NORADCommand
104.6K followers
· 1.8K posts
The Economist
@EconCulture
104.6K followers
· 50K posts
David Harsanyi ✓
@davidharsanyi
104.6K followers
· 65.4K posts
Frequently asked questions about @TencentHunyuan
How many followers does @TencentHunyuan have?
52 302 followers.
How many posts has @TencentHunyuan published?
780 posts.
How do posts by @TencentHunyuan perform?
Collected posts: 18. Views: 3 751 783. Likes: 9 868.