Active Parameters
753.9B
Context Length
1.05M
Modality
Text
Architecture
Mixture of Experts
KV Cache Rate
3744 KB/tok
License
other
Release Date
25 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $1.40 · Output: $4.40
Precision
Context
Workload Memory: 1532.11 GB
FP16 · 8K context
Base Weights: 1500.36 GB
KV Cache: 29.25 GB
Runtime & Graphs: 2.50 GB
16x NVIDIA H200 141GB
1532.1 / 2030.4 GB usable · TP 8 · PP 2
Determine requirements for your specific workload:
Upgrade to Pro
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 5.15.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashMLA |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#22
| Benchmark | Score | Rank |
|---|---|---|
Agentic Index | max 0.53 | 6 |
Agentic Coding | 0.61 | 12 |
Coding Index | max 0.75 | 23 |
General Text | max 1482 | 27 |
Coding | 0.79 | 27 |
General | 0.76 | 28 |
LiveBench Average | 0.76 | 29 |
Web Development | max 1622 | 31 |
Reasoning | 0.86 | 33 |
Agent Arena | max 0.03 | 40 |
Mathematics | 0.88 | 41 |
Data Analysis | 0.70 | 48 |
Intelligence Index | max 0.32 low 0.23 | 88 153 |
Overall Rank
#22
Coding Rank
#28
GLM-5.3 is a large-scale mixture-of-experts language model developed by Zhipu AI / Z.ai utilizing dynamic sparse attention. It provides state-of-the-art multilingual comprehension, complex mathematical reasoning, and coding capabilities.
Attention
Attention Structure
DeepSeek Sparse Attention
Attention Heads
64
Key-Value Heads
64
Attention Head Dimension
192
Position Embedding
ROPE
RoPE Theta
8,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
6,144
Number of Layers
78
FFN Intermediate Size (Dense)
12,288
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
154,880
Mixture of Experts
Total Expert Parameters
51.6B
Number of Experts
256
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
2,048
Dense Layers Before MoE
3
General Language Models from Z.ai