Qwen2.5-32B
Parameters
32B
Context Length
131K
Modality
Text
Architecture
Dense
License
Apache 2.0
Release Date
19 Sept 2024
Knowledge Cutoff
Jun 2024
API Pricing (per 1M)
Input: $0.87 · Output: $0.87
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
131,072 tokens
Consumer
5x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#155
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.38 | 33 |
Professional Knowledge | 0.69 | 44 |
Graduate-Level QA | 0.495 | 104 |
General Text | 1270 | 162 |
Intelligence Index | 0.07 | 218 |
General Knowledge Reference | 0.833 | 17 |
Coding Archived | 0.16 | 19 |
Rankings
Overall Rank
#155
Coding Rank
#125
About Qwen2.5-32B
Qwen2.5-32B is a high-capacity dense transformer from Alibaba Cloud engineered for complex reasoning, long-form content creation, and JSON data parsing. It delivers high stability across diverse system prompts over a 131K token context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
96
Key-Value Heads
8
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
1,000,000
Sliding Window Attention
No
Sliding Window Size
131,072
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
8,192
Number of Layers
60
FFN Intermediate Size (Dense)
27,648
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
152,064
About Qwen2.5
Qwen2.5 by Alibaba is a family of dense, decoder-only language models available in various sizes, with some variants utilizing Mixture-of-Experts. These models are pretrained on large-scale datasets, supporting extended context lengths and multilingual communication. The family includes specialized models for coding, mathematics, and multimodal tasks, such as vision and audio processing.