Mart Roosmaa

Anyone know what happened with the OpenClaw hype?

I have an indian vegetarian cook book that I bought some years back. Every single recipe that I'd like to try from it has at least one impossible to source ingredient...

As I'm getting back into making bread at home, I stocked up on some nice organic flour. Have to figure out where to store all 10kg of it, but I'm already excited for my next bake!

I've been craving borscht for a while now. Finally found some fresh beets at the store today. It's almost ready now! 😋

I'm starting to cultivate microorganisms again. It's been some 4-5 years since my last colony found its end.

My 5yro has figured out how to reliably get past the screen time limiter on Xiaomi TV Box S. On one hand I'm truly proud of that little hacker, on the other hand I'm looking for solutions to workaround the buggy Xiaomi code.

Discovered that Bleach has 3 new seasons I was oblivious of (1000 year blood war), so I've been binging them non-stop. The art style has gotten slight tweaks, but overall it's still following the original Bleach formula. Loving it!

Using Talos in my homelab has made it so stable I've forgotten I actually selfhost a bunch of things. It's boring, in a very good way!

This looks delicious. 😋 No more aws.String-like helpers!

This Christmas vacation I'm tackling the backlog of my Steam library. Some of it at least. The winter sale has already managed to grow it quite a bit.

Gnome has been my desktop of choice for the better part of my life. Giving back a little is the least I can do.

2 of the 6 consumer SSDs (that I bought for my NAS) have died in less than a year. Both of them from the same brand - fanxiang. The other 2 brands - Kingspec & Crucial - are still going strong. Be smart, do NOT trust fanxiang with your data.

Put together a bsky feed for posts related to running AI locally: bsky.app/profile/did:...

Openness for Nemotron includes open evaluation! Eval transparency completes the last puzzle in the E2E repro lifecycle for LLMs. Check out our step-by-step blog on how to use the same pipeline we used for the evaluation of Nemotron 3 Nano through Nemo Evaluator: huggingface.co/blog/nvidia/...

If you've been meaning to give Zed a spin during the slower season, now's the time. Use code ZEDSEASON at checkout for $15 in LLM spend on us. Limited supply, valid through Dec 31. Already using Zed? Share this with someone who needs a nudge.

The main thing Ollama (and LM studio) has going for it, is that everyone has integrated it everywhere. IDEs, Obsidian plugins, self-hostable AI apps.

I tried to give Ollama a fair chance. I was tempted by the automatic VRAM management it does. But everything else is just inferior to llama.cpp. The modelfile concept is just weird. No support for sharded GGUFs. And why use Go templates when all of the ecosystem uses Jinja2?

I did not understand HuggingFace before. I had done some LLM courses out of curiosity, but HuggingFace didn't click. Until I started running things locally. Base models, adapters, fine-tunes, quantizations. I get it now!

At some point I need to more seriously test out ROCm vs Vulkan performance for local models I use. Haven't spent much time on ROCm currently as AMD broke it in the latest linux-firmware release. It has been reverted already, but not sure what the release cadence is there.

llama.cpp just recently merged in (github.com/ggml-org/...) support for serving multiple models, effectively making llama-swap a lot less useful. I love it. Just makes me wonder if llama.cpp is intending to compete with ollama (and LM Studio to some extent).

I wonder.. is it possible to use host @zed.dev's Zeta model locally? 🤔

I wish @zed.dev's Open AI compatible provider support would attempt to auto-detect the models from the server. It's such a chore to manage the models manually in settings.json.

After a bit of experimentation, I've settled on llama-swap and llama.cpp combo to run my local models. LM Studios was a bunch of UI that I wasn't going to use, and having the option to go and tweak every lever that llama.cpp has feels good.

ISP: We see your bandwidth usage has spiked... Me: Oh don't mind me, I'm just downloading some models from HuggingFace.

Got myself @frame.work desktop as an early christmas present. Been having a blast setting it up and playing around with local LLMs.