ERNIE-4.5-0.3B
Parameters
300M
Context Length
131K
Modality
Text
Architecture
Dense
License
Apache 2.0
Release Date
30 Jun 2025
Knowledge Cutoff
Dec 2024
API Pricing (per 1M)
Input: $0.05 · Output: $0.22
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
131,072 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
No evaluation benchmarks for ERNIE-4.5-0.3B available.
Rankings
Overall Rank
-
Coding Rank
-
About ERNIE-4.5-0.3B
ERNIE-4.5-0.3B is an ultra-compact, low-latency dense language model developed by Baidu for edge computing, text completion, and on-device assistants. Released under Apache 2.0, it supports Grouped-Query Attention over a 131K context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
16
Key-Value Heads
2
Attention Head Dimension
128
Position Embedding
Absolute Position Embedding
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
1,024
Number of Layers
18
FFN Intermediate Size (Dense)
3,072
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
103,424
About ERNIE 4.5
The Baidu ERNIE 4.5 family consists of ten large-scale multimodal models. They utilize a heterogeneous Mixture-of-Experts (MoE) architecture, which enables parameter sharing across modalities while also employing dedicated parameters for specific modalities, supporting efficient language and multimodal processing.