Unverified50% confidenceBenchmarkExact time
In the UP host's real-world tests, the generation speed was over 90 tokens per second under a 64K context, dropping to over 60 tokens per second under a 256K context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.78% similarUnverifiedThe theoretical peak of a 56k dial-up modem is approximately 7KB per second.74% similarUnverifiedCloud-based APIs can typically achieve output speeds of tens to hundreds of tokens per second, while consumer-grade GPUs running 27B models often only reach 10–30 tokens per second.71% 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71% similarUnverifiedIn a prefill-only test running gpt-oss-120b on 4× B200s, DWDP4 achieves a 1.92× speedup over DEP4 under the MNT 32K/ISL 32K configuration and a 1.54× throughput improvement at saturation (506K vs. 329K tok/s).71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/979781API
curl https://kongchang.com/api/v1/knowledge/claims/979781MCP
get_claim(id=979781)