Watching Qwen 3.8 Flash w/Strata engine on 2× RTX 3090 24GBs build out RainbowTrends in real time to Javascript on TrendSpider.
Qwen 3.8 Flash Next IQ2_XS dog bones and walking motion.
Blender MCP. It was pretty bad the first time, so I'm having to try it again. It took about 1 hour to create, including the time for editing. Hmm, it's a little strange.
16 GB of unified memory on a MacBook.
Not a rack. Not a rented H100. Alibaba's Qwen team ships Qwen-Image 2.1 with open weights. Community quantizers convert it to GGUF, strip the refusal classifier, and drop 'Qwen-Image-2.1-Uncensored-GGUF' on Hugging Face within days. The
Someone wired an iphone 17 pro max into a 24gb m4 pro macbook over usb-c and split qwen 3.8 27b across both.
Mac alone at 16k context: 109 tok/s prefill. with the phone: 157 tok/s. +44%. at 32k: 101 to 130 tok/s. +29%. the phone also holds part of the kv cache past 64k so the
You have reached the end of the archive
All of qwen38