Llama 3.2 3B
Parameters
3B
Context Length
128K
Modality
Text
Architecture
Dense
License
Llama 3.2 Community License
Release Date
25 Sept 2024
Knowledge Cutoff
Dec 2023
API Pricing (per 1M)
Input: $0.05 · Output: $0.33
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
128,000 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#196
| Benchmark | Score | Rank |
|---|---|---|
Graduate-Level QA | 0.328 | 117 |
General Text | 1166 | 159 |
Intelligence Index | 0.06 | 270 |
General Knowledge Reference | 0.634 | 30 |
Rankings
Overall Rank
#196
Coding Rank
-
About Llama 3.2 3B
Llama 3.2 3B is an efficient on-device language model developed by Meta for mobile AI assistants, writing tools, and localized workflows. It combines 4-bit/8-bit quantization compatibility with a 128K token context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
24
Key-Value Heads
6
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
500,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
Swish
Dimensions
Hidden Dimension Size
2,048
Number of Layers
26
FFN Intermediate Size (Dense)
8,192
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
128,256
About Llama 3.2
Meta's Llama 3.2 family introduces vision models, integrating image encoders with language models for multimodal text and image processing. It also includes lightweight variants optimized for efficient on-device deployment, supporting an extended 128K token context length.