logoalt Hacker News

jonesy827today at 5:19 PM2 repliesview on HN

I've been using the 35B-A3B today for some web scraping work, and it has been on par with Qwen3.8 27B at a much higher speed and at a higher quant (q4 vs q8). I'm impressed.


Replies

jakswatoday at 5:50 PM

I had to go down to UD-Q3_K_XL for Qwen 3.8 27B to get it to fit in VRAM and be usable, but I worry I'm gutting its intelligence somewhat. I too am interested in faster + more-usable alternative that can exchange blows with the Q3-dumbed 27B.

jadboxtoday at 5:25 PM

I need someone to run actual benchmarks between the two.

show 2 replies