Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model
by kroaton on Wednesday April 22, 2026 @04:38PM
(#47869002)
Buy any Strix Halo box and have fun with your 128GB of VRAM.
[ Parent
| on HN ]
Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model
by 2001zhaozhao on Wednesday April 22, 2026 @11:16PM
(#47871936)
I wonder whether it is much more cost-effective in terms of token throughput / hardware+power cost to get actual GPUs instead, given that the model size is only 27B.