Qwen2-7B
Parameters
7B
Context Length
131K
Modality
Text
Architecture
Dense
KV Cache Rate
56 KB/tok
License
Apache 2.0
Release Date
7 Jun 2024
Knowledge Cutoff
Dec 2023
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Context
Workload Memory: 6.20 GB
INT4 · 8K context
Base Weights: 3.26 GB
KV Cache: 0.44 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
6.2 / 21.6 GB usable
1x RTX 3060 12GB
6.2 / 10.8 GB usable
Apple M4 24GB
6.2 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Rankings
Overall Rank
#234
Coding Rank
-
About Qwen2-7B
Qwen2-7B is a foundational open-weights dense model from Alibaba Cloud engineered for general language understanding, coding, and mathematical reasoning. It supports multilingual inputs across 29 languages and context extrapolation up to 131K tokens.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
64
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
Hidden Dimension Size
3,584
Number of Layers
32
FFN Intermediate Size (Dense)
18,944
Tokenizer
Vocabulary Size
152,064
About Qwen2
The Alibaba Qwen2 model family comprises large language models built upon the Transformer architecture. It includes both dense and Mixture-of-Experts (MoE) variants, designed for diverse language tasks. Technical features include Grouped Query Attention and support for extended context lengths up to 131,072 tokens, optimizing memory footprint for inference.