Joined June 2026
- Tweets 160
- Following 68
- Followers 185
- Likes 166
5 Photos and videos
Pinned Tweet
Jun 11
Today I'm launching the CapIX Protocol on EasyA Kickstart.
We are building a compute and inference exchange with an intelligent router.
I hope you guys enjoy it :)
CA: kickstart.easya.io/token/bS5……
More below 👇
Capix.Network (sign up to the waitlist)
17
11
53
7,977
CapIX Protocol retweeted
the future of internet capital markets is already happening.
on kickstart.
"Anybody in the world with an internet connection can own the hottest stock on Earth with nothing but a Solana keypair. That's internet capital markets."
- @mert, live at Solana Summit Germany
9
7
38
1,488
CapIX Protocol retweeted
we love to see long-term founders with good tokenomics 🫡
The CapIX Smart Router is getting ready for launch, and we’re excited about what it means for decentralized compute!
We’ve built a Growth Loop directly into every compute and inference request routed with $CPX:
• 40% burned - helping tighten the supply as the network grows
• 40% to treasury - supporting real infrastructure expansion
• 20% as yield - rewarding the suppliers who power the network
It’s a simple, self-reinforcing system.
This process lets the network strengthen itself with real usage once the Router goes live on Mainnet
CapIX.Network
CA: bS532krUcXBMNqXURPtGqYA7dhEsenYe2z9QKkcEASY
1
2
21
415
The CapIX Smart Router is getting ready for launch, and we’re excited about what it means for decentralized compute!
We’ve built a Growth Loop directly into every compute and inference request routed with $CPX:
• 40% burned - helping tighten the supply as the network grows
• 40% to treasury - supporting real infrastructure expansion
• 20% as yield - rewarding the suppliers who power the network
It’s a simple, self-reinforcing system.
This process lets the network strengthen itself with real usage once the Router goes live on Mainnet
CapIX.Network
CA: bS532krUcXBMNqXURPtGqYA7dhEsenYe2z9QKkcEASY
6
4
14
768
CapIX Protocol retweeted
AI compute is becoming one of the biggest real-world markets on earth.
J.P. Morgan says AI compute demand is exploding and supply is constrained across chips, power and data centers.
Compute is the asset 🔥
$CPX @cpx_token
$ZERO @c0mputeAI
Early gem 🔥
2
5
210
CapIX Protocol retweeted
Jun 13
Around the time gpt4 came out, I said that gpt4 level models would run on consumer hardware. And they do, now. In fact, better. And now I will also say: mythos / gpt 5.5 pro models will run on consumer hardware. Prepare accordingly
117
103
2,864
114,068
Exactly why anyone with idle compute will be able to join our node pool, whether you have a MacBook or a Toshiba. Your compute won’t go to waste and you’ll also earn passively!
Jun 13
A full guide on how to setup this local coding agent on macOS.
Running Gemma 4 26B-A4B and Qwen3.6 35B-A3B locally with llama.cpp, MTP speculative decoding, multimodal support, and PI as a coding agent.
From zero to local AI coding powerhouse in one afternoon.
72tk/s realtime demo with Gemma 4 on MacBook Pro.
- ikyle.me/blog/2026/how-to-se…
1
2
5
434
Don’t worry if you guys can’t build a beast machine to host your AI agents we got you!
HE BUILT A 4-GPU LOCAL AI WORKSTATION BUT OPENCLAW CUT HIS BOT REVENUE BY 5X
assembling a local hardware rig with four high-end GPUs is the dream setup for running autonomous bots. but running the legacy OpenClaw gateway daemon locally choked the GPUs and spiked his power bills
OpenClaw's flat-file memory database forced the local LLM to process massive markdown history strings during every agent call. the bloated context flooded the GPU VRAM and slowed inference speeds to a crawl
Hermes compresses memory using SQLite database searches and loads agent skills dynamically using a three-level hierarchy. the system runs inference on local GPUs using NVFP4 quantization, speeding up execution times by 3x
by keeping the local LLM context clean, the rig ran cool and completed 5x more customer tasks. his daily revenue surged while his hardware operation costs plummeted
Read the full 30-day hardware benchmark and migration guide ↓
1
2
201
$CPX for the win? 👀
wowza.
some crazy cool projects have entered our compute hackathon.
now, it's time for us to select the winner.
see who's in the running on kickstart.easya.io 👀
1
5
186
Jun 13
If you added these nodes on CapIX you could make more 💪
CHINESE DEV STACKED 4 NVIDIA BOXES ON HIS DESK AND MADE $22,000 PROFIT IN YEAR ONE.
Four DGX Spark. Two stacks. One switch connecting all four chips together.
Was paying $1,900 a month for cloud GPUs he would never own.
Bought the hardware once. Electricity dropped to $40 a month. Paid itself off in 6 weeks.
Pause at 0:42 — watch the overlay numbers hit the screen. $1,900 to $40 a month. Paid off in 6 weeks. $22k profit year one. A Chinese dev did this on a regular desk.
Most engineers at big companies rent the same compute and expense it forever.
He owns it and the math compounds every single month.
Buy the hardware. Stack the boxes. Let it print.
Full setup and numbers in the video.
182
Jun 13
Don’t worry if you don’t have the compute to run it locally we got you 👊
Jun 13
Running AI locally has never been more important.
7
204
Jun 13
Easily available with CapIX.network and for a fraction of the price
Jun 13
Best open source model today. Now just need 256GB of VRAM to run it.
6
169
Jun 13
The fact that you’ll have the ability to host them seamlessly on CapIX.network of course!
Jun 13
What about them 👀
2
126
Jun 13
Would cost you a fortune in Claude credits but probably pennies using inference endpoints from Capix.Network 👀
1
3
140
Jun 13
We’re tired of seeing compute budgets get shredded.
Here’s a look at the router in action: 75% real savings on compute costs. This is the fix we need to stop the bleeding.
Who’s with us on this?
CapIX.network
CA: bS532krUcXBMNqXURPtGqYA7dhEsenYe2z9QKkcEASY
3
117
Jun 13
Another great model that will be available on CapIX.Network 💪
.@Kimi_Moonshot's kimi-k2.7-code is now available on Ollama's cloud!
On Ollama's cloud, this model is hosted in the US on the latest NVIDIA B300 datacenter GPUs. Your data stays private and is never trained on.
❤️❤️❤️
Try the model:
Claude:
ollama launch claude --model kimi-k2.7-code:cloud
Codex App:
ollama launch codex-app --model kimi-k2.7-code:cloud
OpenCode
ollama launch opencode --model kimi-k2.7-code:cloud
See the model page on Ollama 👇👇👇
3
96
Jun 13
Just one of the many models available through CapIX
Sign up for early access CapIX.Network
CA: bS532krUcXBMNqXURPtGqYA7dhEsenYe2z9QKkcEASY
Jun 12
MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters
Weights:
huggingface.co/MiniMaxAI/Min…
MiniMax Sparse Attention:
huggingface.co/papers/2606.1…
6
128
Jun 13
I wonder how many people will train their own CapIX hosted LLM
From the amount of support and interest we have so far we’re gonna need a lot more GPu’s 😬
4
125
Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.
GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
docs.z.ai/devpack/latest-mod…
As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks.
API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License.
The future of AI is open, and it belongs to the people.
311
911
7,620
1,771,819