Viewing profile — benbojangles

One day bees will evolve to produce spider venom

70b on my M1 max 64gb

I run a second Mac for local llm use and access it remotely using ssh from the first mac

Omlx needs to incorporate macos native shortcuts use - macos can almost instantly extract text from pdfs and a bunch of other things using it's ane neural engine keeping unified ra…

why combine audio & image analysis into an llm though, why not allow the user to choose their own audio & image analysis alongside their own llm choice?

I run gemma-4-26b-bf16 in mtp mode and it runs very smooth, spitting out answers in seconds and outputting text 30x faster than i can read.

Gemma4 because presumably it does image analysis right? -31b It's a dense model -how many tokens/s is it running at -What temps are the M1 max GPU/CPU running at -Is it mlx or gguf…

Didn't China steal the F-22/F35/B2/C17 blueprints, and also stole COVID?

[dead]

Restoring, updating, upgrading and compiling on a 2014 Jetson TK1 - Running: ai agent cli, ai agent assistant, local llm models.

Anthropic are a smart clever research based bunch of people, they probably realised that openclaw is a mess, full of vibe coding get rich quick people, nothing particularly interes…

Yes I noticed too that several ai agents will tell you directly the code is correct and it is 100 percent fixed but I know it is not true, when I explain to the AI agent that I kno…

I'm running Qwen3.5:0.8b locally on an Orangepi Zero 2w using llama.cpp, runs just fine on cpu only. If I want vulkan GPU I have run qwen3.5:2b locally on a meta quest 3 with zeroc…

You can keep your 512gb mac studio i'm running qwen3.5:0.8b on an Orangepi zero 2w and learning just as much as they are.

i'm running qwen3.5:0.8b on my orangepi zero 2w, low token/s but it still runs. I think i paid around £14 for it over a year ago but now the same board is double price. I wouldn't …

I don't really agree, i am making more money now than ever.

haha this is hilarious

And this is of course tech related because??? If I wanted news I would just check my RSS feed.

Was using Ollama but qwen3.5 unavailable earlier today

100 million euro project - that's around 1/4 of a salvator mundi

Big reveal: they're not but bringing out a feeling of superiority in your enemy inside a warzone makes them easier targets

I love it, first ferarri that i have said "I want one". I have been an ev driver for over a decade and have no regrets, it has improved my life. The mental health benefits of drivi…

Grovia - Lora mesh farming data: https://github.com/benb0jangles/Remote-greenhouse-monitor I hope to add ai data tools & saas, but really I'm just happy to have a running working l…

Live data feed from a greenhouse 3km from base: https://benb0jangles.github.io/Remote-greenhouse-monitor/