GLM-4.6
Active Parameters
357B
Context Length
200K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
MIT
Release Date
30 Sept 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.55 · Output: $2.20
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
42x RTX 4090
24GB VRAM
Datacenter
11x NVIDIA A100
80GB VRAM
Apple Silicon
9x Apple M3 Max
128GB VRAM
200,000 tokens
Consumer
47x RTX 4090
24GB VRAM
Datacenter
13x NVIDIA A100
80GB VRAM
Apple Silicon
10x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#89
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.68 | 17 |
Graduate-Level QA | 0.81 | 49 |
General Text | 1425 | 72 |
Web Development | 1341 | 75 |
Agentic Index | 0.19 | 76 |
Coding Index | 0.46 | 87 |
Intelligence Index | auto 0.18 Standard 0.15 | 140 161 |
Rankings
Overall Rank
#89
Coding Rank
#68
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.
Technical 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
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
Swish
Dimensions
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.