Might have found a killer use for Meta Muse I use the HECK out of Marketplace (I know my GPU brethren also must). Sure Hermes can also do this, but if Muse is doing it it's got integrated access and no risk of being banned.

If you're considering a Spark follow people like @mr_r0b0t, @aijoey and @Tech2Wild there are others I'm forgetting for sure. They're giving the most honest feedback regarding them. From my perspective if you can afford Discrete GPUs always go Discrete GPU. 3090 and up if you can. It's really that simple. There's a reason gpu's have gone up significantly during this time and continue to have price increases along with stock decreases. Nvidia also isn't giving out free 5090's and pro 6000's to creators to review or sell them for a reason. As long as you do your research you'll be happy either way.

Hermes chugging away pricing my game and hardware collection... I'm going to test and allow it to list a few items... will be nice to have something just go through and do all the tedious work. If only AI could box and send items for me as well.

The models aren't the bottleneck anymore. We are. DeepSeek V4 Flash, Qwen 3.8 27B already handle 80-90% of what we actually need. If you're still running the same prompts you did 6 months ago, you're putting zero pressure on the model. Stop waiting on smarter AI. Level up the ask. 🧠

Just a few random 0 shot generative demos for Qwen 3.8 27b! The zombie sim is my favorite due to how well Qwen 3.8 handles hand drawn art. The little guys and animations are so cool!

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what @Alibaba_Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!