Jarkko Sakkinen
jarkko
Edited 19 hours ago
Ordered BCR32. Between 0-2000 EUR I think it's best option :-) Korg SQ-64 is a strong contender tho. Hardware trackers as a product category is one that I've lost completely any interest since I sold OG Polyend Tracker so did not check those. I prefer Renoise and a bit of Octamed 5 via MiSTer.
Ultra top tier priced devices such Cirklon and OXI One are like secret society / cult type of stuff from my perspecive with not that many practical applications ;-) E.g., Cirklon invests to song arrangement, chord generators etc. i.e., stuff that is not very useful in the end ;-) And costs 1750, which 10x the price of BCR32.
Ultra top tier priced devices such Cirklon and OXI One are like secret society / cult type of stuff from my perspecive with not that many practical applications ;-) E.g., Cirklon invests to song arrangement, chord generators etc. i.e., stuff that is not very useful in the end ;-) And costs 1750, which 10x the price of BCR32.
0
0
0
Jarkko Sakkinen
jarkko
I just pretty cool idea on how to scale Helm threads more accurately than i do now based on hardware resources without going in detail with hardware attributes.
I do the thing first tho before mumbling more because then it is fully GPL safe guarded design ;-)
I do the thing first tho before mumbling more because then it is fully GPL safe guarded design ;-)
0
0
0
Jarkko Sakkinen
jarkkoBehringer BCR32 is the first Behringer product that gets me excited ever. I think I will get one :-) I don’t really have hardware sequencer ATM and I’ve lost my interest to hardware trackers after owning Polyend for few years (and i use trackers on desktop already).
BCR32 really hits me as I like Beatstep Pro despite not owning one and BCR32 is like much more advanced version of the same core logic.
0
0
1
@penguin42 @zygoon I've at the same time seen appearance of completely proprietary boxes with similar idea appear on the market with weird subscription deals etc. So before THAT becomes a thing I want to develop a superior solution.
0
0
0
@penguin42 @zygoon 8900 lines in seven'ish months. a shameful number by today's standards ;-)
0
0
0
@zygoon @penguin42 I started to work on this last March when I got my hands on DGX Spark. I booted up NVIDIA DGX OS and was shocked to see that it is not really a hosting platform. It's just a low quality Ubuntu fork with Ollama and shit. Shame on you NVIDIA ;-) They should really should be IMHO.
I looked up at options and OS projects for hosting AI locally are mostly done by AI lunatics with Claude and package random stuff like LM Studio for instance. They have nothing special or any type of architecture to make them particularly feasible hosting LLM workloads.
So I setup a goal that I want an OS that is like my NAS or OpenWRT in my router that focuses providing one service really well with a dedicated machine and that's I've tryin to achieve since :-)
I looked up at options and OS projects for hosting AI locally are mostly done by AI lunatics with Claude and package random stuff like LM Studio for instance. They have nothing special or any type of architecture to make them particularly feasible hosting LLM workloads.
So I setup a goal that I want an OS that is like my NAS or OpenWRT in my router that focuses providing one service really well with a dedicated machine and that's I've tryin to achieve since :-)
2
0
0
Jarkko Sakkinen
jarkko
toolbx confuses me all the time by its name. i'm still not sure am i using toolbx or toolbox lol
0
0
0
@penguin42 [It might be also first Buildroot based operating system ever providing Wayland GNOME desktop]
0
0
0
@penguin42 https://gitlab.com/puu-os/bootc this is what i'm trying to get in condition for the context
1
0
0
Jarkko Sakkinen
jarkko
@penguin42 nope :-) the key factor here is good reference point not the AI model itself. and getting comprative figures. i just picked one. now i can focus e.g. litellm issues ;-) and see how concurrent sessions work. many things to polish.
1
0
1
Jarkko Sakkinen
jarkko
@zygoon My target is a bit different than picking the best model.
Qwen 3.8 is a great reference model for testing a hosting platform, as it is fairly popular and when you combine Qwen 3.8 27B and Bonsai 2 27B you have wide set of quantization of the same base model.
Hosting any model is a small subproject by itself which depends on many variables such as hardware platform and hosting stack. And bunch of random peeking and poking as things develop rapidly and documentation lags behind.
That said, I'm aware of the Laguna model and Poolside, which is one of more relevant and interesting AI startups from US ;-)
Qwen 3.8 is a great reference model for testing a hosting platform, as it is fairly popular and when you combine Qwen 3.8 27B and Bonsai 2 27B you have wide set of quantization of the same base model.
Hosting any model is a small subproject by itself which depends on many variables such as hardware platform and hosting stack. And bunch of random peeking and poking as things develop rapidly and documentation lags behind.
That said, I'm aware of the Laguna model and Poolside, which is one of more relevant and interesting AI startups from US ;-)
1
0
1
Jarkko Sakkinen
jarkko
Edited yesterday
Test prompted with machine having RTX 4090 24 GiB and Puu OS hosting Bonsai 2 27B. Seems to work :-)
0
0
2
Jarkko Sakkinen
jarkko
Edited yesterday
Bonsai 2 27B with 256k context running on RTX 4090 24 GiB, and hosted by Puu OS.
Puu OS also has preconfigured Qwen 3.8 27B, which fits easily to DGX Spark.
LLM models, when you actually host them, require their own (manual) shoehorning in order to fly nicely in the environment, and there is no exact template for this. Thus, I focus on one all-arounder model with two different quantizations in the base installation of Puu OS. For those that don't know this Bonsai 2 27B is a ternary quantization of Qwen 3.8 27B.
This is a personal achievement for me despite not being a huge achievement overall as I could never imagine I could have a something with a decent context size with the hardware that I have at hand.
I purposely want to do a small AI assisted contribution with this to kernel when I have a chance :-)
Puu OS also has preconfigured Qwen 3.8 27B, which fits easily to DGX Spark.
LLM models, when you actually host them, require their own (manual) shoehorning in order to fly nicely in the environment, and there is no exact template for this. Thus, I focus on one all-arounder model with two different quantizations in the base installation of Puu OS. For those that don't know this Bonsai 2 27B is a ternary quantization of Qwen 3.8 27B.
This is a personal achievement for me despite not being a huge achievement overall as I could never imagine I could have a something with a decent context size with the hardware that I have at hand.
I purposely want to do a small AI assisted contribution with this to kernel when I have a chance :-)
2
0
1
@bughuntercat_ a system where some or more equal than others never plays out well.
0
0
0
Jarkko Sakkinen
jarkko
Edited 3 days ago
You cannot morally and ethically sustainable software distribution ecosystem with these two conditions being true at the same time:
1. Proprietary software distribution.
2. Ban of the use of AI tools in software development.
This is why I don't think Flatpak is in the "right side of history".
1. Proprietary software distribution.
2. Ban of the use of AI tools in software development.
This is why I don't think Flatpak is in the "right side of history".
1
0
0
Jarkko Sakkinen
jarkko
It's a shame that Caustic is dead other than running it under Wine. It's still the best mobile DAW workflow.
0
0
0
Jarkko Sakkinen
jarkko
I did not know how much there would be work in writing a rock solid installer for an operating system before I did one for Puu OS.
Here's in high-level what it does :-)
Here's in high-level what it does :-)
0
0
0
Jarkko Sakkinen
jarkko
I missed the whole OpenCode 2 thing until I started to get reports about it. The truth is that I have not used a lot of AI lately.
My peaks with AI happen when I work on AI tools ;-)
My peaks with AI happen when I work on AI tools ;-)
1
0
0