A 27 billion parameter AI model running on a $300 GPU with just 8GB of memory.

That's what Unsloth's new quantization has achieved with Qwen 3.8 27B — straight to PC, no cloud, no subscription.

The DOOM GuyAug 31

Qwen 3.8 flash next just made 125B parameters look cheap.

The wild part isn’t its size. It’s how little of that size it needs every time it thinks. The Architecture: → 125B main parameters → Only 6B activated per token → Another 51B parameters in its Engram embedding

Julian Goldie SEOAug 31

I tested GLM 5.3 Flash and Qwen 3.8 Flash on two DGX Sparks.

One model crawled. The other built a playable game. Here’s the honest answer on whether local AI coding is worth the hardware.

BridgeMind HighlightsAug 31

The local Qwen 3.8-Flash-Next comparison.

Wayne LowryAug 31