GLM-4-9B-Chat-1M
Parameters
9B
Context Length
1M
Modality
Text
Architecture
Dense
KV Cache Rate
40 KB/tok
License
MIT License
Release Date
30 Jun 2024
Knowledge Cutoff
Jan 2024
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Context
Workload Memory: 7.00 GB
INT4 · 8K context
Base Weights: 4.19 GB
KV Cache: 0.31 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
7.0 / 21.6 GB usable
1x RTX 3060 12GB
7.0 / 10.8 GB usable
Apple M4 24GB
7.0 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for GLM-4-9B-Chat-1M available.
Rankings
Overall Rank
-
Coding Rank
-
About GLM-4-9B-Chat-1M
GLM-4-9B-Chat-1M is a specialized open-weights model by Z.ai engineered for ultra-long document analysis and multi-hour transcript processing. It delivers high needle-in-a-haystack retrieval accuracy across a massive 1M token context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
32
Key-Value Heads
2
Attention Head Dimension
128
Position Embedding
Absolute Position Embedding
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
4,096
Number of Layers
40
FFN Intermediate Size (Dense)
13,696
Tokenizer
Vocabulary Size
151,552
About GLM Family
General Language Models from Z.ai