Re:Qwen 3.6 27B is the sweet spot for local development
by anon373839 on Tuesday June 30, 2026 @01:05AM
(#48728670)
Can you mention what inference stack you're using? I've tried MTP several times with that model and it always seems to significantly cut my token generation speed from ~60 tokens/sec to ~40 (M3 Max).
[ Parent
| on HN ]
Re:Qwen 3.6 27B is the sweet spot for local development
by jasonjmcghee on Wednesday July 01, 2026 @07:43PM
(#48754598)
(see above reply to myself) I misattributed the gain from dflash - it was dflash-mlx library + mlx model, not dflash itself giving me the speedup.