Unverified50% confidenceBenchmarkExact time
Gemma量化模型在高性能笔记本电脑上Token生成速度可达每秒20-50个，纯CPU推理约5-15 tokens/秒，INT4量化下NVIDIA RTX 4060/4070可将推理速度提升3-5倍
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
Valid until: 10/14/2026
Sources
Related Claims
UnverifiedAfter INT4 quantization, the Qwen3-0.6B model file is only about 400 MB, retains approximately 95% of baseline capability, and an ordinary laptop CPU can achieve a generation speed of 10–30 tokens per second.78% similarUnverified在配备96GB显存的M2 Max上以1-bit精度运行时，简单任务生成速度稳定在约28-30 tokens/秒76% similarUnverifiedOn the RTX 5090, Muse Glimmer's generation speed increases from 75 tokens per second to 233 tokens per second, a speedup of approximately 3.1×.75% similarUnverifiedThe Gemma 4 26B MOE version achieves an actual inference speed of 60 tokens per second on a GPU with 24GB of VRAM.72% similarUnverifiedCollapse推理速度：CPU上单条10-token上下文约0.23毫秒，MPS在batch 1024下约230万token/秒，最近邻查询约0.48毫秒72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/530560API
curl https://kongchang.com/api/v1/knowledge/claims/530560MCP
get_claim(id=530560)