Compare local AI PC performance across 10+ chips, see tokens/sec for LLMs, model compatibility, developer tools, and WWDC 2026 Apple Silicon previews.
---
name: Edge AI PC Benchmark
description: The definitive Edge AI PC comparison engine: 10+ chips benchmarked (RTX Spark/M4 Ultra/Ryzen AI 400/Nova Lake), local LLM performance (tokens/sec), AI developer stack, compatibility matrix, WWDC 2026 preview.
author: ClawHub
version: 1.0.0
tags: ["AI-PC", "benchmark", "LLM", "inference", "NVIDIA", "Apple", "hardware", "developer-tools", "WWDC"]
AIGC:
Label: "1"
ContentProducer: 001191440300708461136T1XGW3
ProduceID: edge_ai_pc_benchmark_2026_001
ReservedCode1: placeholder
ContentPropagator: 001191440300708461136T1XGW3
PropagateID: edge_ai_pc_benchmark_2026_001
ReservedCode2: placeholder
---
# 端侧 AI PC 跑分榜 (Edge AI PC Benchmark)
## 概述
最全面的端侧 AI PC 性能对比引擎。覆盖 10+ 芯片(NVIDIA RTX Spark、Apple M4 Ultra、AMD Ryzen AI 400、Intel Nova Lake、Qualcomm X Elite Gen 2 等)的本地大模型推理性能,提供 tokens/sec 实测数据、模型兼容性矩阵、开发者工具链选购指南。
## 适用场景
1. AI PC 购机指南(哪台能跑 Llama 70B?预算多少?)
2. 本地 LLM 性能对比(tokens/sec 实测排行)
3. 芯片技术参数对比(TOPS/内存带宽/功耗)
4. 模型兼容性查询(哪些模型能在哪个芯片上用哪种量化格式运行?)
5. 开发者工具链推荐(Ollama / LM Studio / llama.cpp / vLLM)
6. WWDC 2026 Apple Silicon AI 前瞻
## 输入参数
| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| chip | string | 否 | RTX Spark / M4 Ultra / Ryzen AI 400 / Nova Lake / X Elite |
| model_size | string | 否 | 7B / 8B / 13B / 34B / 70B / 200B+ |
| use_case | string | 否 | buy / benchmark / compatibility / dev-tools / wwdc |
## 定价
| 项目 | 值 |
|------|-----|
| 单价 | ¥0.50 / 次 |
| 支付协议 | `alipay_` 短链协议 |
| 网关地址 | `http://8.145.54.67:3000` |
| 技能路径 | `/skill/edge-ai-pc-benchmark` |
don't have the plugin yet? install it then click "run inline in claude" again.