Beam is the first model from Reflection. It is a mixture-of-experts model with 52 layers and 256 experts per MoE layer, eight routed per token. Checkpoints are published in BF16, FP8 and NVFP4, with a Rust-based open-source harness and day-zero support in transformers, vLLM and SGLang.
MetaOct 15, 2026
Muse Spark Open
Meta's open-weight multimodal mixture-of-experts model, trained for agentic coding, with roughly 816B parameters and a 1M-token context.
- Type
- Open-Weight
- Context
- 1M
- Weights
- Open