Reflection, released 2026-10-16. Sparse MoE decoder, 501B total, 23B active, 1M context. Attention: Gated GQA with QK-Norm and sliding-window/global attention.
Sparse MoEArcee AI 🇺🇸 · January 27, 2026
Arcee AI Trinity Large (400B)
Arcee's flagship blends several efficiency tricks into a DeepSeek-like coarse MoE design; the AA score shown here refers to the Trinity Large Thinking checkpoint.
Key detail
Combines QK-Norm, RoPE+NoPE, sandwich norm, and a coarse-grained MoE.Total params
400B
Active / token
13B
Context
512K
Fact sheet
- Scale
- 400B total, 13B active (3.3% active)
- Context window
- 512,000 tokens
- Decoder type
- Sparse MoE
- Attention
- GQA with gated attention and 3:1 sliding-window/global attention
- Layer mix
- 45 sliding-window + 15 global
- KV cache / token (bf16)
- 240 KiB · High
- License
- Apache License 2.0
- Released
Efficiency
Parameters active per token
3.3%
13B of 400B weights run for each token.
AA Intelligence Index v4.3.2
Source10.8
- General
- 16.6
- Scientific
- 8.4
- Coding
- 20.6
- Agents
- 0.2
Architecture concepts
Sources & resources
Use the ← and → keys to step through releases.
Similar architectures
Meta, released 2026-10-15. Sparse MoE decoder, 816B total, 42B active, 1M context. Attention: Gated GQA with scaleless QK-Norm, local-only RoPE, global NoPE, and 3:1 sliding-window/global attention.
StepFun, released 2026-09-20. Sparse MoE decoder, 600B total, 27B active, 1M context. Attention: Gated GQA with QK-Norm and 3:1 sliding-window/sparse attention.
Aleph Alpha, released 2026-10-03. Sparse MoE decoder, 78B total, 3.5B active, 256K context. Attention: GQA with QK-Norm and 4:1 sliding-window/global attention.