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

Unverified85% confidenceFactTime unknown

RTX 5090上Qwen3.6 35B-A3B推理速度达220 token/s，显存占用约23GB

1

Sources

85%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026

Sources

Qwen3.6 MTP加速实测：单GPU推理飙到220 token/s

bilibili普通鱼学家呀

Related Entities

RTX 5090product Qwen3.6 35B-A3Bmodel

Related Claims

UnverifiedRTX 5090上Qwen3.6 27B模型预填充速度从174提升到253 token/s，显存占用约18GB90% similar Unverified在24GB显存的显卡上运行Qwen3.6 27B模型，未经优化可达每秒约40个Token的生成速度，优化后可达50-60 Token/s78% similar Unverified对于RTX 4090（24GB显存），WhichLLM可能会推荐Qwen3.6 27B的Q5量化版本，预计推理速度约为每秒27 Token76% similar UnverifiedQ4_K_M量化文件大小17.77GB，pp2048速度96.8 tok/s，tg128速度11.4 tok/s75% similar Unverified在显存充足、模型完整驻留GPU时，RTX 4090跑Q4量化的27B模型通常可达15～30 tokens/s；触发CPU卸载后速度可能骤降至1～2 tokens/s甚至更低75% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/18061

API

curl https://kongchang.com/api/v1/knowledge/claims/18061

MCP

get_claim(id=18061)