A single 3090 running Qwen 3.8 27b at 220 t/s + 150k context
Q8 on weights and KV cache Let the bastard think 😈
Perplexity runs AI locally on your device 🔥
Perplexity announced a new feature for Pro and Max subscribers called Portable Computer, which runs on the NVIDIA DGX Spark device. I mean! Instead of sending your requests to remote cloud servers, you can run AI models locally on the device itself. That means
Tried it on a single b70 after picking one up before using your configuration for qwen 3.8 27b, it’s been great.
I just successfully completed the coolest thing I've done so far with AI using Qwen 3.8 27B NVFP4 for NInfer.
I had it reverse engineer Starlight Precise 2.6, the best video upscaler so I can run it natively in Linux. It was previously being used inside Wine. This seems to have
You have reached the end of the archive
All of qwen38