Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified75% confidenceFactTime unknown

MiniCPM和Qwen-0.5B等1B以下轻量模型配合INT4量化可以在手机芯片上运行

1

Sources

75%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

中文预训练模型资源库：覆盖LLM与多模态的5500+ Star开源项目

githublonePatient

Related Entities

MiniCPMmodel Qwen-0.5Bmodel

Related Claims

VerifiedQLoRA引入4-bit量化技术，使得在单张24GB显存的RTX 3090/4090上微调650亿参数级别的模型成为可能71% similar UnverifiedQwen-7B经过4-bit量化后，一张搭载24GB显存的消费级显卡即可流畅运行71% similar UnverifiedMiniMax M3主打轻量化，单卡即可运行，适合小微企业客服和简单问答场景71% similar Unverified在M4 24GB设备上，9B模型（如qwen3.5-32k:9b-mlx）运行速度快、内存占用小，但无法有效发现代码问题70% similar UnverifiedQwen3-0.6B 经 INT4 量化后模型文件仅约 400MB，保留约 95% 基准能力，普通笔记本 CPU 即可实现每秒 10-30 token 生成速度69% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/29980

API

curl https://kongchang.com/api/v1/knowledge/claims/29980

MCP

get_claim(id=29980)