Beam
Reflection AI's 501B-parameter mixture-of-experts model with 23B active, in a waitlisted beta API, with Apache 2.0 weights announced.
0 members list Beam, unchanged over the last 12 weeks, data as of 7 October 2026
Usage on Stackness
0membersunchanged over the last 12 weeks
Members who list Beam in their Stack, by week.
Nobody has this tool in their stack yet.
Posts about Beam
- Mistral Large 4 vs Beam vs Kolibri: which open weights you can download, and what your hardware can serve
Only Kolibri's weights are out. Beam and Mistral Large 4 stay API previews until late October, and Kolibri's 4-bit build runs at 50 tok/s on a 64GB Mac.