tweetindex
RU

IoTeX ✓

@iotex_io · U.S.A. 🇺🇸 · joined 22 Dec 2017

The blockchain platform for Real-World AI.

326 062Followers
244Following
7 115Posts total
205.6KViews on collected posts

Последние посты

Local AI is advancing faster than anyone expected. When an everyday Mac Mini running on @rapidmlx delivers output quality matching an H100 cloud cluster, the marginal cost of AI approaches zero—breaking Big Tech’s monopoly on compute and data. Local Compute + Distributed 8.3K views · 51 likes · 6 reposts · 2 replies Open on X →
The mighty H100 vs. a humble 2023 Mac mini M2 Pro. 🥊 Running FLUX.2 klein 4B locally via rapid-mlx. Look at the output—the visual difference is practically zero. You don't need a massive data center to get top-tier AI generation anymore. Power to the local AI. 💻✨ https://t.co/ 9K views · 14 likes · 2 reposts · 2 replies Open on X →
170K+ models. 25M developers. ModelScope just amplified a Rapid-MLX build driven by the @iotex_io dev community. 🌐⚡️ A top lab open-sourced the weights. An independent crew optimized them for Apple Silicon (36–42% faster, full 262K context, 45/45 checks). A global hub shipped 20.7K views · 361 likes · 15 reposts · 52 replies Open on X →
Rapid-MLX releases Qwen3.8-Flash-Next-4bit, an MLX quantization for running Qwen3.8-Flash-Next locally on Apple Silicon. 🤖 https://t.co/T0lgZKTADe ⚡ Native MTP speeds up generation by 36–42%, reaching 34.85 tok/s in the measured Mac Studio setup. 🧠 Preserves the upstream https:/ 10.2K views · 76 likes · 4 reposts · 9 replies Open on X →
Don't miss the third post in this thread.A Mac mini that boots straight into a local model before anyone logs in. It restarts itself, serves an OpenAI-compatible endpoint, and never sends a byte off-device. That isn't just an app anymore. That's a node. 🌐 It's an always-on 8.1K views · 51 likes · 6 reposts · 5 replies Open on X →
Rapid-MLX 0.13.4 is officially out — and local inference just got a massive speed boost. 🚀 Qwen3.5/3.6/3.8 now automatically select verified MTP + continuous speculative batching, delivering 14–31% higher throughput under concurrent workloads. On Qwen3.8-27B, single-request http 23.1K views · 419 likes · 99 reposts · 55 replies Open on X →
SEC Chair Paul Atkins says the CLARITY Act is headed for a Senate vote on September 15, a potentially historic step toward making America the “crypto capital of the world.” 11.5K views · 214 likes · 5 reposts · 36 replies Open on X →
@iotex_io When will this nightmare end? We're getting poorer every day, and you're just talking nonsense.🤬 230 views · 9 likes · 1 reposts · 0 replies Open on X →
⬇️ Try it in one line: brew install rapid-mlx Apache-2.0, MLX-native. 3.4k ⭐ and counting. ⭐️ https://t.co/sBuizNhQRh 1.5K views · 14 likes · 5 reposts · 0 replies Open on X →
🚀 Rapid-MLX 0.11.0 is here. The fastest local AI engine for Apple Silicon just got faster: 25.6x faster TTFT with prefix-cache reuse. And smarter: it no longer just runs models, it runs agents - point it at your tools and it works on its own. Tool calls are schema-valid by ht 71.9K views · 1K likes · 137 reposts · 120 replies Open on X →
@iotex_io @nubilanetwork @DeCharge__ @TheJamGalaxy @ROVR_Network @FlashbackSocial @captur_network @GenpulseAI @getaxal @TraxaIO @Lilypad_Tech @avodotso @DGramNetwork Good initiative 166 views · 4 likes · 1 reposts · 1 replies Open on X →
https://t.co/16lBhlVPtj 10.8K views · 41 likes · 9 reposts · 1 replies Open on X →
Phase 1 of Crypto’s Got Talent is complete. 13 projects are moving on to compete for $500K. Shoutout to the semifinalists: @nubilanetwork @DeCharge__ @TheJamGalaxy @ROVR_Network @FlashbackSocial @captur_network @GenpulseAI @getaxal @TraxaIO @Lilypad_Tech @avodotso @DGramNetwork
0:13
30.3K views · 243 likes · 71 reposts · 64 replies Open on X →

На фоне аккаунтов своего размера

7 постов за последние 90 дней рядом с диапазоном 100K–1M подписчиков. показывается большему числу людей, чем аккаунты того же размера.

Медианные просмотры10 150этот аккаунт5 983медиана для 100K–1M
Охват, %3.11%этот аккаунт1.49%медиана для 100K–1M
Вовлечённость, %0.90%этот аккаунт0.93%медиана для 100K–1M
ПоказательЭтот аккаунтМедиана для 100K–1MОтношение
Медианные просмотры на пост10 1505 9831.70×
Охват (просмотры ÷ подписчики)3.11%1.49%2.09×
Вовлечённость0.90%0.93%0.97×

Другие в этом диапазоне →   Сравнить с другим аккаунтом →   Как считаются эти ориентиры →

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

30.3K5 May
10.8K
166
71.9K29 Jul
1.5K
230
11.5K2 Sep
23.1K3 Sep
8.1K
10.2K
20.7K
9K4 Sep
8.3K

Last 13 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.28%5 May
0.47%
3.61%
1.81%29 Jul
1.25%
4.35%
2.23%2 Sep
2.50%3 Sep
0.78%
0.90%
2.08%
0.22%4 Sep
0.71%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.

What the audience does

Likes76.7%2 542 in total
Reposts10.9%361 in total
Replies10.5%347 in total
Quotes0.6%21 in total
Bookmarks1.3%42 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.

Похожие аккаунты