Tencent, released 2026-08-28. Sparse MoE decoder, 770B total, 49B active, 1M context. Attention: Gated MLA with DeepSeek Sparse Attention and IndexCache.
Sparse MoEZ.ai 🇨🇳 · June 17, 2026
GLM-5.2 (744B)
Long-context GLM refresh that keeps the 744B sparse MoE backbone and adds IndexShare for 1M-token DSA inference.
Key detail
Reuses each full DSA indexer result across the next three layers, making 1M-token sparse attention cheaper.Total params
744B
Active / token
40B
Context
1M
Fact sheet
- Scale
- 744B total, 40B active (5.4% active)
- Context window
- 1,048,576 tokens
- Decoder type
- Sparse MoE
- Attention
- MLA with DeepSeek Sparse Attention and IndexShare
- Layer mix
- 78 MLA/DSA
- KV cache / token (bf16)
- 87.8 KiB · Moderate
- License
- MIT License
- Released
Efficiency
Parameters active per token
5.4%
40B of 744B weights run for each token.
AA Intelligence Index v4.3.2
Source33.7
- General
- 36.9
- Scientific
- 31
- Coding
- 26.1
- Agents
- 37.5
Architecture concepts
Sources & resources
Use the ← and → keys to step through releases.
Similar architectures
Mistral AI, released 2026-10-29. Sparse MoE decoder, 1T total, 52B active, 1M context. Attention: MLA with modified DeepSeek Sparse Attention, index reuse, and KV sharing.
Z.ai, released 2026-02-11. Sparse MoE decoder, 744B total, 40B active, 198K context. Attention: MLA with DeepSeek Sparse Attention.
Z.ai, released 2026-04-07. Sparse MoE decoder, 744B total, 40B active, 198K context. Attention: MLA with DeepSeek Sparse Attention.