I Am #AliveAndThriving Today! || #IAmAliveChallenge || Daily Off-Grid Jungle Journal Entry: Day #1424 - Major Successes and Steps Forward with Running Two Larger AI Models on My Laptop - Lower Puna, Far East Big Island, Hawai'i - Friday, June 12, 2026

I live naked and barefooted, very close to Earth and Nature, in an 18-acre, off-grid, clothing-optional, food-forest intentional community (GaiaYoga Gardens), way out in the jungles of Lower Puna, far East Big Island, Hawai'i, and I have for more than 7 years now. Although there are many challenges, I love my life, and I'm immensely grateful to live where and how I do, on my own terms! I would not want to live any other way! 😁🙏💚⚡💥🔥✴️✳️❇️👣🌱✨🤙

Hive Debt: 25.60%

HIVE Fiat-Dollar Price: 0.050 USD

HBD/HIVE-Backed Dollar Fiat-Dollar Price: 0.962 USD

ALIVE SWAP.HIVE Price: 0.02324377 SWAP.HIVE 

HEARTBEAT ALIVE Price: 0.10953268 ALIVE

BLURT Fiat-Dollar Price: 0.00072647 USD

QORT Fiat-Dollar Price: 0.149435 USD

VOI Fiat-Dollar Price: 0.0001313 USD

BTC/Bitcoin Fiat-Dollar Price: 64,253.6 USD

BCH/Bitcoin Cash Fiat-Dollar Price: 207.64 USD

LTC/Litecoin Fiat-Dollar Price: 43.875 USD 

Gold Fiat-Dollar Price: 4,218.85 USD 

Silver Fiat-Dollar Price: 68.00 USD 

Ranking for Our @aliveandmmb Witness Node: #125 (among all witnesses, including inactive)/#99 (among active witnesses only)/653.3k HP in votes/50 votes in total

Warm greetings all! 😁🙏💚✨🤙

Since my post yesterday, in which I mentioned my success in getting Gemma 4 26B-A4B QAT up and running successfully on my laptop using llama.cpp as the backend LLM server, I've made some even more significant strides in this regard. That was a huge win, and a notable step forward, especially considering that I was previously running Gemma 4 E4B and Gemma 4 E4B QAT, a much smaller model indeed.

With the help of Grok (on X), a very important realization regarding the seemingly missing run flags in the two llama.cpp forks, ik-llama.cpp and llama-cpp-turboquant, and a a fair bit more research and testing last night and this morning, I'm happy to say that I am now able to successfully run both Gemma 4 26B-A4B QAT and Qwen3.6 26B-A4B APEX IQuality on my laptop in a very functional and stable manner. So two larger MoE (Mixture of Experts) models, one with 26 billion parameters, and the other with 35 billion parameters, can be successfully loaded and run on a system with 8GB of VRAM. The 64GB of RAM, and the 13th-generation i9-13900HX Core Intel CPU, definitely strongly support making this possible.

Now that I'm able to load and run both of these larger models stably, my primary focus is refining and optimizing the specific run flags, to see if I can squeeze more performance out for fewer used system resources. I also still want to compare the practical performance and resources use between ik-llama.cpp and llama-cpp-turboquant.

From what I can see, there don't seem to be many people that are attempting to run larger AI models on computers with low VRAM, 6-8GB, though I have found a few that have found ways to accomplish this successfully, and I've certainly gleamed some very useful information from what they've shared, which I've implemented and tweaked for my own setup. It's still pretty wild that I'm doing all this off grid in the jungle...

It's only been about 2 months since I've begun running, experimenting with, and testing AI models on my laptop, and around 1.5 months since diving into working with Hermes Agent, and I can say definitively that I have indeed made multiple huge steps forward in that short time. I've also fried my brain learning all the important details, and and how they fit together into a functional whole. With my new successes with Gemma 4 26B-A4B QAT and QWEN3.6 35B-A3B APEX IQuality, for which I feel quite triumphant, I can see clearly that this was very much worth the focus and effort.

Yesterday, Friday, I left the Flow House, after finishing up my Hive-Blurt-'We Are Alive Tribe' tasks, by just after 3PM, giving my attention first to some photography for my posts, and then to a few small jungle-community tasks, including going on a banana hunt around the property, in search of harvestable banana racks, of which I found one, and clearing a spot along along the central trail to dig another planting hole for bananas. I finally headed to Wabisabi in the early evening, where I made myself some food, and collected my leftover superfood fire coffee from the fridge, before returning to the Flow House to do more research on llama.cpp build and run flags, and to begin my evening Hive tasks. I got through all of my notifications by just before 9:30PM, and after another successful round of AI research and testing, I went to bed by around 11:45PM. I woke up just before 7AM, having slept fairly well, going to prepare my superfood fire coffee in Wabisabi, then heading back to the Flow House to do more successful AI research and testing, and to write this post. It's now just before 2PM, so it's a really good time to wrap this up, so that I may attend to my few other important Hive-Blurt-'We Are Alive Tribe' tasks, before leaving the Flow House a little later in the afternoon, to focus first on some photography for my posts, and then on some jungle-community/land work and tasks. I deeply appreciate y'all so very much! Untitl tomorrow's iteration of these posts! Always forward, onward, upward, and whaleward, ho, together we go! 😁🙏💚✨🤙

2026 Life Goals

1.) Do regular integral practices again, alone or with others.

2.) Prepare regular batches of my medicinal teas collected from the land again.

3.) Make my plant nursery, and the gardens, beautiful again.

4.) Begin learning relevant coding/programming languages to more fully contribute to the sovereignty-driven technologies where I am active, like Arch Linux, Hive, Qortal, DeSo, and Bastyon.

All photos were taken with my Motorola G Play 2024 Android Phone.

Thank you all so much who have helped me get to where I am today, and allowing me to share more of the beauty and magic from my life and my world with you, and for your continuous appreciation and support! I am truly deeply grateful! 😁🙏💚✨🤙

If you'd like to find me on other alternative platforms where I have accounts (I spend most of my time here on Hive), click on this signature image below to go to my LinkTree page.

Come join us in the We Are Alive Tribe on Hive and on Blurt!

Image created by @benthomaswwd

You're invited to provide liquidity in our two ALIVE diesel/liquidity pools, both of which offer daily liquidity rewards:

• ALIVE:SWAP.HIVE

• ALIVE:ALIVEM

• ALIVE:HEARTBEAT

There will be more ALIVE pools coming soon!

Vote for our @aliveandmmb Witness Node!

This is our collaboratively shared Witness node between the We Are Alive Tribe, and @borniet's and my MMB (Maximum Mutual Benefit) Project, here to build something good for all of us! The higher in the witness ranking we go, the more that we'll be able to grow the We Are Alive Tribe, and the more that we'll be able to share with all of you!

If you appreciate what we're doing with the We Are Alive Tribe, and feel inspired and motivated to lend a hand in building and growing our decentralized community economy and financial framework, which benefits all of us, community conntributions/donations/investments may be sent to our 'We Are Alive Tribe Sovereign Wealth Investment Fund' account, @waat-swif. They're deeply appreciated, and are put to very good use.

Vote for @borniet's @botlord Witness Node!

Bjorn is our badass coder who hosts and manages our (and also Bradley's) community backends, he creates all sorts of useful tools, and he assists people all over the Blockchain constantly. He redefines the term 'busy'!

Vote for @bradleyarrow's Witness Node!

Bradley's tenaciously committed and all-in on Hive for the long haul (just like me!), and the higher his witness goes in the ranking, the higher the weekly BBH and BBHO dividend payouts will be!

Join the worldwide Satsman Army! It's by far the best, most fun, inspiring, and motivating way to earn Bitcoin/BTC!

Signature image created by @doze, and the dividers made by @thepeakstudio, with all tweaked to their present form by me.