All the sources are in the body of the post. Windows being in free fall is at least questionable to me, because in the source, StatCounter, windows usage has mostly been replaced by ‘unknown’.

Found it by looking up dark mode Firewatch wallpapers.

Edit: Didn’t find higher resolutions of this specific one. But here are slightly different but higher resolutions variants: https://imgur.com/a/jvkoP

And the second one in this list

https://unsloth.ai/docs/models/qwen3.6#mtp-guide
Unsloth made a guide and has graphs with comparisons

You can also contribute to OpenStreetMap in your area using simple apps like StreetComplete or EveryDoor. This has a way lower barrier to entry than contributing code in my opinion. And it has the immediate benefit of a better local map for a LOT of services that are built on top of OSM.

I’m European and had to do the same so it’s based on something else.

Don’t know about Ubuntu specifically but for all software I actually want to work, I wait for the first point release upon a major release.

Artificial Analysis just posted their results and there seems to be a similar increase in output token usage as the 35B model.

Ah, I don’t know anything about Windows. I’m using Linux and both the latest ROCM (7.2.2) and latest vulkan (26.0.5) packages work without issues for combined gaming and AI. My reported numbers were with Vulkan at zero context for reference.

I’ve been using it for the past few days and the output quality seems to be on par or slightly better than 3.5 27b. The biggest issue is the token usage that has exploded with this revision. It can easily reason for 20k-25k tokens on a question where the qwen3.5 models used 10k. Since it runs more than 3 times faster, it still finished earlier than the 27b, but I won’t have any context/vram left to ask multiple questions.

Artificial Analysis has similar findings.

I agree with the suggestion of the other commenters, just wanted to add that I personally run llama.cpp directly with the build in llama-server. For a single-user server this seems to work great and is almost always at the forefront of model support.

I’m running it with the UD_Q4_K_XL quant on 24GB VRAM 7900XTX at ~120-130* token/s. Since it’s an MOE model, CPU inference with 32 GB ram should be doable, but I won’t make any promises on speed.

*Edit: I had a configuration issue on my llama.cpp that reduced the performance. It was limited to 85 tk/s but that was user error on my part.

AllenAI has released open source models with open training data, code and science. If you value the ‘source’ to actually be open. They’ve also published the multimodal Molmo models.

I got some weird specialised hardware over USB working via WinBoat. Might be an option for some.

Unfortunately, the AI community prefers rushed buggy development over proper, tested releases, so the quants and maybe the PR weren’t fully working.

As of 3 hours ago, unsloth was still updating their quants and guide. I don’t have time to test now but I wouldn’t judge the base model performance in the first few days when the bugs are still being worked out.

They also recommend some unconventional parameters in the Unsloth guide.

It could also be that the model is truly shit of course.

Edit I just took a look at the llama.cpp repo and there are still issues with the implementation as well.

Seems to be a new architecture so custom support is needed.

Tracking issue

PR

I can only speak for the Heroic launcher but this has been my experience:

• One click play button like Steam, but it’s easier to configure Linux-specific settings in the menu.
• Updates are done automatically or can be forced like Steam.
• Cloud saves are available, but need to be done manually from the game settings menu with the risk of user error.
• There is a friends list and chat, but the games I played had their own in-game friends list.
• Unfortunately, no achievements from what I’ve seen.
• No DRM, so you truly own the game. (as far as it’s possible to own something digital.)
• Linux game support seems to not be any worse than Steam
• Built-in Wine/Proton version installer.