Qwen3.6-27B that you can run on a laptop outperforms Qwen3.5-397B which was a flagship model requiring a commercial grade server that was released in February

☆ Yσɠƚԋσʂ ☆@lemmy.ml · 1 day ago

Qwen3.6-27B that you can run on a laptop outperforms Qwen3.5-397B which was a flagship model requiring a commercial grade server that was released in February

☂️-@lemmy.ml · 13 hours ago

did you guys run it? how much vram do you have?

☆ Yσɠƚԋσʂ ☆@lemmy.ml · 5 hours ago

It depends on what precision you run it at. For 4 bit, you need at least 16 GB VRAM and ideally 24 GB to be comfortable, for the full 16 bit you’d need at least 54gb. A RTX 4090 is minimum. I’ve got 64gb myself, so I can run 8 bit quant comfortably.

AlHouthi4President@lemmy.ml · 17 hours ago

🫡🇨🇳

geneva_convenience@lemmy.ml · 20 hours ago

How does it compare to gemma4?

☆ Yσɠƚԋσʂ ☆@lemmy.ml · 19 hours ago

I tried gemma4 and wasn’t that impressed with it. Qwen 3.6 seems to be a lot more capable.

Qwen3.6-27B that you can run on a laptop outperforms Qwen3.5-397B which was a flagship model requiring a commercial grade server that was released in February

Qwen3.6-27B that you can run on a laptop outperforms Qwen3.5-397B which was a flagship model requiring a commercial grade server that was released in February

Qwen Studio