The consensus right now is that Qwen3.6 in its 27B and 35B-A3B versions is better for coding whereas Gemma4 is stronger when it comes to OCR, audio transcription and the likes. Margins are slim though and the harness at these model sizes is the most important factor.
I can see that and I don't know your setup, but there are people pushing >70t/s with MTP on a single 3090, with big contexts still >50t/s. 64k is not a lot for agentic coding, and IIRC 128k with turboquant and the likes should be possible for you. r/LocalLLM/ and r/LocalLLaMA/ are worth a visit IMO.
"[...] In the coming days, we will also open-source smaller-scale variants, reaffirming our commitment to accessibility and community-driven innovation. [...]"
It‘s mainly due to system requirements that Flux.2-dev doesn’t get same usage as Z-Image. A 5090 needs about a minute to generate an image with a basic workflow with Flux.2-dev. But prompt adherence and scene/character consistency in edit mode is (way) ahead of Qwen-Edit-2509 if you ask me.
The Bene Gesserit was something I couldn't quite get a grip on, the gravitas house Atreides' arrival seemed to have, when they came to Arrakis, the different houses and their relationships... I had a lot of moments where felt I was missing context, because the scenes presented themself as "important" but I couldn't figure it out in that moment. Sometimes later in the movie some context was given, but during those scenes I felt "lost". I will certainly give it rewatch, maybe even read the books now.
As someone who loves Denis Villeneuve I did all that, although I felt "left behind" throughout the movie, because I didn't read the books. Visually amazing, but I was sad I couldn't appreciate it the way it could have been.