Pangu Pro MoE 72B

Overview

Huawei's first open-weight release, a 72B MoE optimized for Ascend silicon. Strong on enterprise code and Chinese business scenarios, but the custom Pangu license needs careful review.

When to pick this model

• Deployments already running on Huawei Ascend hardware
• Enterprise code and business workflows in Chinese markets
• Research on non-NVIDIA training and inference stacks
• Workloads where Huawei's ecosystem integration matters

VRAM requirements by quantization

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

• First-class optimization for Ascend NPUs
• Solid enterprise code and business reasoning
• Open weights from a major hyperscaler
• MoE design keeps inference tractable

Limitations

• Around 42 GB VRAM in Q4
• 32k context trails modern flagships
• Custom Pangu license requires legal review
• Tooling outside Huawei's stack is thin

Architecture & training

Architecture: MoE · 72B · Huawei PanGu Pro · proprietary architecture

Training: Huawei — specialized in enterprise code and CN business scenarios.

Quick start

ollama pull hf.co/huawei/pangu-pro-moe-72b-GGUF

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