4 points | by cmrdporcupine 4 hours ago
2 comments
this 3.5 Super is still below Qwen 3.8 next as they state themsleves
they also released an interesting smaller model https://news.ycombinator.com/item?id=50104922 3.5 bolt it uses 2bit quantization and beats the other small active layer models
LiLiCorr spec decode + Mamba blocks seem really interesting for the speed up.
this 3.5 Super is still below Qwen 3.8 next as they state themsleves
they also released an interesting smaller model https://news.ycombinator.com/item?id=50104922 3.5 bolt it uses 2bit quantization and beats the other small active layer models
LiLiCorr spec decode + Mamba blocks seem really interesting for the speed up.