Parameters
32B
Context Length
131K
Modality
Text
Architecture
Dense
KV Cache Rate
159 KB/tok
License
Apache 2.0
Release Date
19 Sept 2024
Knowledge Cutoff
Jun 2024
API Pricing (per 1M)
Input: $0.87 · Output: $0.87
Precision
Context
Workload Memory: 18.65 GB
INT4 · 8K context
Base Weights: 14.90 GB
KV Cache: 1.25 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
18.6 / 21.6 GB usable
2x RTX 4090 24GB
18.6 / 43.2 GB usable · TP 2
Apple M3 Pro 36GB
18.6 / 27.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.43.1
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#180
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.38 | 34 |
Professional Knowledge | 0.69 | 45 |
Graduate-Level QA | 0.495 | 104 |
Intelligence Index | 0.07 | 285 |
General Knowledge Reference | 0.833 | 16 |
Coding Archived | 0.16 | 19 |
Overall Rank
#180
Coding Rank
#144
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.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
96
Key-Value Heads
8
Position Embedding
ROPE
RoPE Theta
1,000,000
Sliding Window Attention
No
Sliding Window Size
131,072
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
8,192
Number of Layers
60
FFN Intermediate Size (Dense)
27,648
Tokenizer
Vocabulary Size
152,064
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.