Parameters
6B
Context Length
33K
Modality
Text
Architecture
Dense
KV Cache Rate
28 KB/tok
License
ChatGLM3-6B Model License
Release Date
27 Oct 2023
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
Precision
Context
Workload Memory: 5.51 GB
INT4 · 8K context
Base Weights: 2.79 GB
KV Cache: 0.22 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
5.5 / 21.6 GB usable
1x RTX 3060 12GB
5.5 / 10.8 GB usable
Apple M4 24GB
5.5 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
No evaluation benchmarks for ChatGLM3-6B-32K available.
Overall Rank
-
Coding Rank
-
ChatGLM3-6B-32K is an extended-context variant of ChatGLM3 engineered for long-form document comprehension and multi-turn enterprise dialogue. It utilizes an adjusted base frequency RoPE mechanism to maintain coherence over a 32K context window.
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
Base Precision
BF16
Hidden Dimension Size
4,096
Number of Layers
28
FFN Intermediate Size (Dense)
13,696
Tokenizer
Vocabulary Size
65,024
ChatGLM series models from Z.ai, based on GLM architecture.