Unverified50% confidenceBenchmarkExact time
Going from 16G to 24G of VRAM, median decoding speed jumps from 56.8 tok/s to 98.3 tok/s, a 73% increase.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
141 Real-World Benchmarks Revealed: How Fast Can Your GPU Really Run Large Models?
bilibili九物AI生产力10/23/2026
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.77% similarUnverifiedThe generation speed officially given for 2.5-24 is 184 characters per second.74% similarUnverifiedAdding a third card to a dual-card setup increased decoding by only 1% or even had a negative effect; 128K domain fill speed dropped from 57 to 22.95 tok/s.74% similarUnverifiedIn 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.74% similarUnverifiedGPT-OSS-20B BF16 loading was reduced from 545 seconds to 70 seconds (7.8× speedup), and Qwen3.5-397B achieved a 1.93× to 2.3× improvement.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092287API
curl https://kongchang.com/api/v1/knowledge/claims/1092287MCP
get_claim(id=1092287)