I swear I was shocked by what I saw. Qwen 3.8 27B Q4 is now running on an RTX 4060 with 8GB VRAM only, and it is unlocked...

I swear I was shocked by what I saw. The Qwen 3.8 27B Q4 is now running on an RTX 4060 with only 8GB VRAM, and it has a window of 64,000 tokens open, which after showing its size on the disk only takes 14.6GB thanks to the new IQ4_XS technology from Unsloth. ← Generation speed is 150 tokens per second, and reading is 5 tokens per second...

ابو سعود 💻Aug 19

FINALLY! Qoder already supports Fable 5

For just one thousand Rupiah, you can experience the latest Top Models such as GLM 5.3 + Qwen 3.8 Max, let alone Fable 5 Just get straight to it:

D4NNBOZAug 191

Qwen 3.8 27B might be the most interesting local AI release I've tested this month.

27.78B parameters. 262K context. Apache 2.0. And it beat Claude Opus 4.6 Max on 15/19 launch benchmarks. But I wanted to see what happens outside benchmarks.

Julian Goldie SEOAug 19

“Not caring, it just does stuff.”

Pretty remarkable view of what qwen 3.8 uncensored is doing

Herb ScribnerAug 19