Unverified50% confidenceFactExact time
The correlation coefficient between VRAM capacity and decoding speed is R=0.41 (moderate correlation), and between total VRAM plus system memory capacity and speed is R=0.13 (essentially no correlation).
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
UnverifiedInference speed (tokens/second) ≈ memory bandwidth ÷ model size72% similarUnverifiedAt a scale of 1 million vectors, PRISM achieves 99% recall and 15 milliseconds median latency on a 2GB c8g.medium; HNSW on a 4GB c8g.large is 392 milliseconds, with building taking about 21.7 hours and exhibiting memory thrashing.69% similarUnverifieddecode阶段的生成速度近似等于内存带宽÷模型大小，例如在内存带宽273GB/s的M4 Pro上运行4GB的Q4量化7B模型理论最大生成速度约68 tokens/s68% similarUnverifiedWhen extending the context from 192,000 to 256,000, the expert cache dropped from 16.44 GB to 13.66 GB and KV increased from 4.31 GB to 7 GB, with almost zero speed cost, because KV is fully in VRAM and the expert cache automatically balances.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092286API
curl https://kongchang.com/api/v1/knowledge/claims/1092286MCP
get_claim(id=1092286)