GLM-4.6
Active Parameters
357B
Context Length
200K
Modality
Text
Architecture
Mixture of Experts
KV Cache Rate
368 KB/tok
License
MIT
Release Date
30 Sept 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.50 · Output: $2.00
Hardware & System Requirements
Precision
Context
Workload Memory: 729.94 GB
FP16 · 8K context
Base Weights: 724.57 GB
KV Cache: 2.88 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
8x NVIDIA H200 141GB
729.9 / 1015.2 GB usable · TP 8
Determine requirements for your specific workload:
Upgrade to Pro
Runtime requirements
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.54.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Architecture Diagram
Evaluation Benchmarks
Rank
#120
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.68 | 18 |
Graduate-Level QA | 0.81 | 62 |
General Text | 1424 | 94 |
Coding Index | 0.46 | 95 |
Web Development | 1342 | 102 |
Intelligence Index | auto 0.18 Standard 0.15 | 180 208 |
Rankings
Overall Rank
#120
Coding Rank
#95
About GLM-4.6
GLM-4.6 is a 357B Mixture-of-Experts model developed by Z.ai activating 32B parameters for advanced coding, UI generation, and agentic search. It delivers enhanced token efficiency and bilingual reasoning across a 200K token context window.
Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
96
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
Absolute Position Embedding
RoPE Theta
1,000,000
Normalization
RMS Normalization
Activation Function
Swish
Dimensions
Base Precision
FP16
Hidden Dimension Size
5,120
Number of Layers
92
FFN Intermediate Size (Dense)
1,536
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
151,552
Mixture of Experts
Total Expert Parameters
32.0B
Number of Experts
160
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
1,536
Dense Layers Before MoE
3
About GLM-4
GLM-4 is a series of bilingual (English and Chinese) language models developed by Zhipu AI. The models feature extended context windows, superior coding performance, advanced reasoning capabilities, and strong agent functionalities. GLM-4.6 offers improvements in tool use and search-based agents.