RT @bnjmn_marie: Gemma 4 12B ist schwer zu quantisieren. Ich konnte kein GGUF unter 6,4 GB finden, das gut funktioniert. MoQ 4.25 ist immer noch ziemlich gut und spart im Vergleich zu UD Q4KXL 0,9 GB. Unterhalb dieses Wertes würde ich keines der anderen GGUFs empfehlen, die ich bewertet habe. mehr auf Arint.info #Gemma4 #GGUF #LLM #MoQ #Quantisierung #UDQ4_K_XL #arint_info https://x.com/bnjmn_marie/status/2064097932459069716#m
Related
FYI: WPP Media sees AI as advertising's $1.3 trillion growth engine in 2026: WPP Media's midyear forecast projects 4.4% ...
FYI: WPP Media sees AI as advertising's $1.3 trillion growth engine in 2026: WPP Media's midyear forecast projects 4.4% global ad growth to $1.3 trillion, as AI investment offsets ...
New CloudBees report is out. AI tools boost output but create risks. 81% of teams see more production incidents, and tes...
New CloudBees report is out. AI tools boost output but create risks. 81% of teams see more production incidents, and test maintenance is now a huge burden. We get more code, but we...
so when will Fedi start banning promotion of "AI"? Plenty of "ethical enthusiasts" around here, running "local", "open m...
so when will Fedi start banning promotion of "AI"? Plenty of "ethical enthusiasts" around here, running "local", "open models", making morons out of themselves#ai #llm #fediverse #...