Back to GLM-5.3-Flash in the gallery

Z.ai

Natively multimodal GLM refresh, previously previewed as Ox Alpha, that replaces most MLA/DSA layers with Kimi Delta Attention and adds four-stream mHC.

GLM-5.3-Flash architecture diagram
GLM-5.3-Flash architecture diagram. Select the diagram to view it at full size.

Architecture and specifications

Scale
320B total, 18B active (5.6% active)
Context (tokens)
1,048,576
Vocabulary
154,880 (~155k)
License
MIT License
Date
2026-08-26
Decoder type
Sparse hybrid
Attention
3:1 Kimi Delta Attention (Q/K L2 normalization) and MLA with DeepSeek Sparse Attention
Layer mix
34 KDA + 11 MLA/DSA + 1 MTP layer
KV cache / token (bf16) info
11.6875 KiB · Very low
Key detail
Mixes 34 Kimi Delta Attention layers with 11 MLA/DSA layers and routes residuals through four mHC streams.

Training and benchmarks

Pretraining data
30T-token multimodal corpus Reported corpus size for a newly trained base; a separate tokens-seen total is not given. GLM-5.3 Flash release
Post-training methods
RL The release describes frontend-coding RL with environment feedback; other alignment stages are not itemized. GLM-5.3 Flash release
AA Intelligence Index v5.0 info
Total score 27.8 Knowledge Work 43.7 Coding 23.7 Science 12.5 General 30.9
AA Intelligence Index v4.3.2 info
Total score 41.8 General 39.7 Scientific 27.6 Coding 42.2 Agents 53.0

Further reading and tools