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

Unverified50% confidenceFactExact time

14B MoE模型的代码能力保留了95.9%，损失仅约4%

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/2/2026

First Seen

Valid until: 9/30/2026

Sources

Qwen3.6非官方衍生模型：34B深度扩展与14B极致压缩解析

bilibiliAI观模者6/21/2026

Related Claims

Unverified开发者最终选择KL散度最低（0.028）的变体，GSM8K下降1.83%，MMLU保持不变，HarmBench合规率从30.8%提升至100%65% similar Unverified14B MoE模型基于Qwen3.6 35B MoE压缩而来，总参数从35B压缩到14B，但每次激活参数仍为3B，与原版35B完全一致62% similar Unverified14B MoE模型是越狱版本，KLD（与原模型的差距指标）仅为0.0015（约0.15%）61% similar UnverifiedOmniMerge V4在MBPP代码测试中达到73.4%，相比原版Q6K量化的56.2%提升了15.8个百分点61% similar UnverifiedLing-3.0-flash 采用混合专家（MoE）架构，激活比例仅约4%（124B总参数中激活约5.1B）60% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/40893

API

curl https://kongchang.com/api/v1/knowledge/claims/40893

MCP

get_claim(id=40893)