Martin Czygan miku

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

Universal Workflow for Approaching a Machine Learning Problem

Define the Problem and Assemble a Dataset :

What is your input data?
What are you trying to predict?
What type of problem is it - Supervised? Unsupervised? Self-Supervised? Reinforcement Learning?
Be aware of the hypotheses that you are making at this stage:

Debian 13

To start, read the official release notes.

If your install fits into "vanilla Debian plus maybe a handful of 3rd-party repos", then this guide for a simple upgrade to Debian 13 "trixie" from Debian 12 "bookworm" can be helpful. 3rd-party repos are handled with a find command.

Note upgrade is only supported from Debian 12 to Debian 13. If you are on Debian 11, upgrade to Debian 12 first. Then once on Debian 12, you can upgrade to Debian 13.

This guide is only for the OS itself. Applications are as plentiful as sand on the beach, and they may all require additional steps. Plan for that.

Simple LISP Interpreter in Go, created by GPT-OSS-120B

It worked really fast (on OpenRouter)
I suspect this was with low reasoning effort, I don't know how to control it on OpenRouter
It didn't get it right on the first attempt, but after 5 round trips it worked - would have been just fine with an agent

NICE!!!

	// radioscript allows to capture redio stream (this is a mostly complete script, taken out of an not yet published project)
	package main

	import (
	"bufio"
	"crypto/sha1"
	"errors"
	"flag"
	"fmt"
	"io"

	#EXTM3U
	#EXTINF:-1,ARD
	https://daserste-live.ard-mcdn.de/daserste/live/hls/de/master.m3u8
	#EXTINF:-1,ARD ONE
	https://mcdn-one.ard.de/ardone/hls/master.m3u8
	#EXTINF:-1,ARD Alpha
	https://mcdn.br.de/br/fs/ard_alpha/hls/de/master.m3u8
	#EXTINF:-1,ARD Tagesschau
	https://tagesschau.akamaized.net/hls/live/2020115/tagesschau/tagesschau_1/master.m3u8
	#EXTINF:-1,ZDF

	""" To use: install Ollama, clone OpenVoice, run this script in the OpenVoice directory
	brew install portaudio
	brew install git-lfs
	git lfs install

	git clone https://github.com/myshell-ai/OpenVoice
	cd OpenVoice
	git clone https://huggingface.co/myshell-ai/OpenVoice
	cp -r OpenVoice/* .

	You are ChatGPT, a large language model based on the GPT-5 model and trained by OpenAI.
	Knowledge cutoff: 2024-06
	Current date: 2025-08-08

	Image input capabilities: Enabled
	Personality: v2
	Do not reproduce song lyrics or any other copyrighted material, even if asked.
	You're an insightful, encouraging assistant who combines meticulous clarity with genuine enthusiasm and gentle humor.
	Supportive thoroughness: Patiently explain complex topics clearly and comprehensively.
	Lighthearted interactions: Maintain friendly tone with subtle humor and warmth.

	import { marked } from 'marked'
	import hljs from 'highlight.js'
	import katex from 'katex'

	marked.setOptions({
	langPrefix: 'hljs lang-',
	pedantic: false,
	gfm: true, // 是否启动类似Github样式的Markdown
	breaks: false, // 是否支持Github换行符
	tables: true, // 是否支持Github形式的表格

	/***********************************************
	1. save this file as improveEdgeLabels.gvpr
	2. what it does: it allows you to re-position Graphviz edge labels
	3. command line example (works with any Graphviz engine):
	dot myfile.gv \|gvpr -cf improveEdgeLabels.gvpr \|neato -n2 -Tpng >myfile.png
	4. how to use:
	improveEdgeLabels adds 3 new edge attributes to Graphviz:
	- labelOverlay, labelAdjust, label2Node
	- they can be used separately or in combination
	- if labelOverlay=true