RT @JoelDeTeves: Testing @DJLougen "Ornstein" 27B - Q4_K_M Harmonic (same author) already felt like the smartest Qwen3.5-27B variant I'd tested. However *THIS* model @ Q4 feels much more intelligent than it has any business being. Here is my layman's understanding of the difference (I might be completely wrong - I am not a neuroscientist): - Both draw from the same high-quality "premium" reasoning traces (exactly 799 premium examples in both cases). These traces are deep (~1,667 words on average), statistically validated, and engineered to include self-correction (100% of rows), verification, and exploration of alternatives. - However, the key difference is that Harmonic-27B uses *only* the 799 premium traces, whereas Ornstein-27B builds on those same 799 premium traces and *adds 430 curated degenerate traces* (total 1,229). In other words it deliberately includes examples of bad reasoning - loops, restating without progress, filler, superficial padding, so the model learns what effective thinking is *not*. Absolute mad science happening here. Follow @DJLougen for more! Speed: 31 tokens/second (good) Mmproj -> Unsloth/Qwen3.5-27B (image recognition tested and works great) VRAM usage: 21.6 GB Configuration: -m Ornstein-27B-Q4_K_M.gguf --mmproj mmproj-F16.gguf --n-gpu-layers 99 --ctx-size 262144 --cache-type-k turbo4 --cache-type-v turbo4 --fit on --jinja --reasoning-format auto --flash-attn on Using @spiritbuun TurboQuant fork of Llama.cpp - running @ max context to test the limits of this version and see where context rot starts to happen. Also worth follow! Next test: will it perform in…

Mehr auf Arint.info

#for #gguf #Llama #Llamacpp #max #science #the #Unsloth #arint_info

https://x.com/JoelDeTeves/status/2041761720520339545#m

randomly found this while browsing the Alpine repository: ecasound. I've been dreaming of a simple and composable suite of programmes for manipulating live audio. the workflow of #max/msp, #puredata and the like never felt natural to me.

Ecasound is a software package designed for multitrack audio processing. It can be used for simple tasks like audio playback, recording and format conversions, as well as for multitrack effect processing, mixing, recording and signal recycling

The basic working principle of ecasound is similar to the widely used gdb (software debugging) and mysql (database admin) tools. Ecasound allows the user to perform most common tasks directly from the terminal console

now I want to try this so much, hoping there’s a guide or a book or something.

#DSP