Alibaba Cloud, released 2026-04-15. Hybrid MoE decoder, 35B total, 3B active, 256K context. Attention: 3:1 Gated DeltaNet and Gated Attention.
Dense hybridAlibaba Cloud 🇨🇳 · April 22, 2026
Qwen3.6 (27B)
Dense Qwen3.6 model that keeps the Qwen3.5-style Gated DeltaNet/Gated Attention hybrid stack while replacing MoE blocks with dense FFNs.
Key detail
Uses a 64-layer dense hybrid layout with 48 DeltaNet layers and 16 full-attention layers.Parameters
27B
Context
256K
KV / token
64 KiB
Fact sheet
- Scale
- 27B parameters
- Context window
- 262,144 tokens
- Decoder type
- Dense hybrid
- Attention
- 3:1 Gated DeltaNet and Gated Attention
- Layer mix
- 16 gated attention + 48 DeltaNet
- KV cache / token (bf16)
- 64 KiB · Low
- License
- Apache License 2.0
- Released
Efficiency
Parameters active per token
100%
Dense: every weight runs for every token.
AA Intelligence Index v4.3.2
Source21.4
- General
- 31.5
- Scientific
- 12.1
- Coding
- 21.4
- Agents
- 17.8
Architecture concepts
Sources & resources
Use the ← and → keys to step through releases.
Similar architectures
Ornith, released 2026-08-23. Hybrid MoE decoder, 35B total, 3B active, 256K context. Attention: 3:1 Gated DeltaNet and Gated Attention.
Alibaba Cloud, released 2025-09-09. Hybrid MoE decoder, 80B total, 3B active, 256K context. Attention: 3:1 Gated DeltaNet and Gated Attention.
Bad Theory Labs, released 2026-07-20. Dense hybrid decoder, 27B parameters, 256K context. Attention: 3:1 Gated DeltaNet and Gated Attention.