Unverified50% confidenceFactExact time
Adding 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.
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
UnverifiedGoing from 16G to 24G of VRAM, median decoding speed jumps from 56.8 tok/s to 98.3 tok/s, a 73% increase.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.72% similarUnverifiedIn BF16 configuration (two 48GB GPUs), decoding speed ranges from 25.1 tok/s at 1K to 23.9 tok/s at 128K, with almost no degradation.72% similarUnverified13B–14B class models (4-bit quantization) see speeds drop to 2–5 tokens per second under this configuration69% similarUnverifiedIn Path C, an RTX 3080 paired with a DGX Spark improves Prefill speed from 1111.3 to 1600 (approximately 44%), but Decode speed drops from 33.36 token/s to 17.62 token/s.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092289API
curl https://kongchang.com/api/v1/knowledge/claims/1092289MCP
get_claim(id=1092289)