reflection/Beam-1.0-501B-A23B
main boardmodel
Beam is an open model built by Reflection. Mixture-of-experts, 501B total, 23B active (256 experts, 8 per token). Context: 1M tokens (config). License: apache-2.0.
- Org
- reflection
- Released
- 2026-10-07
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 501.3B total, 23.0B active
- Architecture
- MoE · 256 experts, 8/token · BeamForCausalLM
- Context
- 1,048,576 tokens
- Task
- text-generation · text
- Signal
- 258 HF likes · 5510 downloads · 1 X post(s)
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~309.2 GB: Mac 512GB
- Q8 ~535.5 GB: no listed device
- FP16 ~1005.4 GB: no listed device
Links
First published here 2026-10-07 · updated 2026-10-07 · markdown · JSON