ERNIE 4.5 300B-A47B

Overview

Baidu's first open release at frontier scale: a 300B MoE with 47B active parameters. Strongest open model for Chinese, with partial weight publication.

When to pick this model

• Chinese-language production workloads at frontier quality
• Multilingual applications targeting East Asian markets
• Research benchmarking against Western open models
• Long-context analysis up to 128k tokens

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	180 GB
Q5_K_M	215 GB
Q8_0	320 GB
FP16 (no quantization)	600 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Best-in-class Chinese-language performance
• Efficient MoE inference with 47B active
• 300B total parameters at frontier scale
• 128k context window

Limitations

• Around 180 GB VRAM at Q4
• Baidu license has commercial restrictions
• Limited adoption and support outside China
• Only partial weights publicly released

Architecture & training

Architecture: MoE · 300B · ERNIE 4.5 · Baidu PaddlePaddle

Training: Baidu — massive Chinese corpus + multilingual. Weights partially released.

Quick start

# Déploiement complexe — vérifier la licence Baidu avant usage

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.