Expired50% confidenceBenchmarkExact time
In LOD generation testing, Mixar generated three levels—LOD0, LOD1, and LOD2—with textures reduced from 4K to 2K and 1K, creating a total of 52 new textures, with results meeting expectations.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
Related Claims
Unverified在27B混合架构、4B稠密模型、36B MoE三类模型上以8k上下文测试，Prefill阶段性能无变化，Decode阶段打补丁后快约1.4%66% similarUnverifiedIn the benchmark tests, each repository was run 4 times on each side and the median was taken.62% similarUnverifiedIn mixed-precision training, each FP16 parameter occupies 2 bytes of GPU memory, and each FP32 parameter occupies 4 bytes of GPU memory.61% similarUnverifiedAVX-512 instructions can complete multiply-add operations on 16 float32 values in a single instruction, delivering more than tenfold throughput improvement compared to scalar loops60% similarUnverified叠加cv=5的5折交叉验证后，144种参数组合需训练144×5=720次模型60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/261200API
curl https://kongchang.com/api/v1/knowledge/claims/261200MCP
get_claim(id=261200)