I Am #AliveAndThriving Today! || #IAmAliveChallenge || Daily Off-Grid Jungle Journal Entry: Day #1415 - Running and Testing LLMs at the Edge of My Laptop's Limits, and I'm Loving SearXNG - Lower Puna, Far East Big Island, Hawai'i - Wednesday, June 3, 2026

4 hours ago

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: 22.82%

HIVE Fiat-Dollar Price: 0.056 USD

HBD/HIVE-Backed Dollar Fiat-Dollar Price: 0.958 USD

ALIVE SWAP.HIVE Price: 0.02094166 SWAP.HIVE 

HEARTBEAT ALIVE Price: 0.11259691 ALIVE

BLURT Fiat-Dollar Price: 0.00090409 USD

QORT Fiat-Dollar Price: 0.163197 USD

VOI Fiat-Dollar Price: 0.0001529 USD

BTC/Bitcoin Fiat-Dollar Price: 63,307.3 USD

BCH/Bitcoin Cash Fiat-Dollar Price: 249.76 USD

LTC/Litecoin Fiat-Dollar Price: 46.015 USD 

Gold Fiat-Dollar Price: 4,482.35 USD 

Silver Fiat-Dollar Price: 74.05 USD 

Ranking for Our @aliveandmmb Witness Node: #126 (among all witnesses, including inactive)/#98 (among active witnesses only)/641.2k HP in votes/50 votes in total

Warm greetings all! 😁🙏💚✨🤙

I've been working with Hermes Agent for just over one month now, and with locally-run AI models/LLMs for just about a month and a half, and while much is possible, and I've made some good progress, effectively working with the hardware limitations of my laptop, especially only having 8GB of VRAM, has been quite challenging indeed, and at times quite frustrating. The low VRAM means that I need to run smaller models with good quantization, which directly impacts their effectiveness regarding what I need them to do. I push to the very edge, in my quest to find a solidly reliable and capable agentic-AI setup that fits what I'm attempting to do. That is indeed still a work in progress.

If I were using larger and more capable cloud-based models, I would likely be able to make much more substantial and rapid progress, but I'm not willing to pay to make use of them. There are multiple platforms that allow limited free use of various very good models, though the rate limits can be problematic, so it's a good idea to set up multiple, to allow for load balancing and swapping on the fly, as needed. I still haven't tried to set this up yet, partly due to a lack of time, and partly because I really don't like the idea of my information and data passing through and being recorded by the hosting service providers.

I was finally able to successfully load and test a new model, aside from my usual Gemma-4-E4B, and one that I just discovered, Holo3.1-4B-I1, which is a new multimodal that uses the famous Qwen3.5 as its base. My initial tests with it have been mixed, as it uses more VRAM, which makes the context overflow more quickly. I'm still in the process of finding workable parameters with it, but it does hold some promise.

Context represents how much an LLM can hold and process at once, and it is directly connected to, and limited by the amount of VRAM on a system's video card. That's a bit of a bugger, because Hermes Agent requires a minimum of context of 64k, which notably raises the VRAM usage. Finding just the right balance is more than a little challenging, but I'm learning quickly, and my results are indeed slowly improving as I progress.

On a more evenly-positive note, since installing, setting up, and configuring SearXNG (an open-source, private, personal/local, and programmable meta-search engine) on my laptop the night before last, I've been happily surprised, and quite impressed by its capabilities. I figured out how to correctly set it as the default search provider in my most-used browser, Vivaldi, so now any search queries that I type in Vivaldi are automatically run using my local SearXNG instance. I now have no direct need for any external search providers, as all searches are done locally and privately. That's pretty freaking cool, I've got to say.

Yesterday, Wednesday, after finishing up my Hive-Blurt-'We Are Alive Tribe' tasks by around 1PM, I prepared for a session that was scheduled for 1:30PM. The session started slightly late, it went well, and we wrapped it up by just before 6PM, after which I made myself some food in Wabisabi, collected my leftover superfood fire coffee from the fridge, and with those in hands, I headed back to the Flow House to begin my evening Hive tasks. I got everything done by a bit after 10PM, and after working with Hermes a bit more, and doing some more agentic-AI research, I went to bed by just after 12:15AM. I woke up by just before 7AM, having slept fairly well, going to prepare my superfood fire coffee in Wabisabi, then returning to the Flow House, to experiment with LLM-loading parameters in LM Studio, to do a bit more LLM/agentic-AI research, and finally to write this post. It's now just before 1:45PM, so it's an excellent 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! Until tomorrow's manifestation 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:

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!