Alibaba Cloud, released 2026-08-14. Dense hybrid decoder, 27B parameters, 256K context. Attention: 3:1 Gated DeltaNet and Gated Attention.
Dense hybridBad Theory Labs 🇳🇬 · July 20, 2026
BTL-3 (27B)
Agent-oriented Qwen3.6-27B derivative that adds a rank-32 LoRA adapter for coding, structured tool use, and long multi-turn execution.
Key detail
Retains Qwen3.6-27B's 64-layer hybrid stack while adapting its attention, DeltaNet, and FFN projections through rank-32 LoRA.Parameters
27B
Context
256K
KV / token
64 KiB
Fact sheet
- Scale
- 27B base + 934 MB LoRA adapter
- 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.
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 2026-08-26. Hybrid MoE decoder, 125B total, 6B active, 256K context. Attention: 3:1 Gated DeltaNet and Qwen Sparse Attention (QSA).
Liquid AI, released 2026-10-27. Dense hybrid decoder, 1.7B parameters, 256K context. Attention: ShortConv plus gated GQA with QK-Norm and sliding-window/global attention.