List your company

Language Model Evaluation on LM Evaluation Harness (test)

74.22MMLUE2E
67.959269.584671.2172.8354May 6, 2026

Evaluation results

MethodLinks
E2EModel=Qwen2.5-7B-Ins, Peak Mem (GB)=75.39, Step Time (s/step)=1.712026.0574.2256.0166.7288.781.2364.5275.22
LoPTModel=Qwen2.5-7B-Ins, Peak Mem (GB)=59.66 (↓21%), Step Time (s/step)=1.56 (↓9%)2026.0574.1859.766.3889.0981.464.8375.4
BaseModel=Qwen2.5-7B-Ins2026.0574.1757.366.7283.4779.3564.7574.51
LoPTModel=Qwen3-4B-Base, Peak Mem (GB)=32.89 (↓23%), Step Time (s/step)=1.32 (↓7%)2026.0570.123.8462.2988.6369.9554.6266.85
BaseModel=Qwen3-4B-Base2026.0570.0723.8457.8485.1465.6254.8567.56
E2EModel=Qwen3-4B-Base, Peak Mem (GB)=42.55, Step Time (s/step)=1.422026.0570.0124.0362.0388.3568.7654.7867.17
LoPTModel=Llama-3.1-8B-Ins, Peak Mem (GB)=47.54 (↓24%), Step Time (s/step)=1.65 (↓21%)2026.0568.5547.0361.4382.480.4754.1177.35
E2EModel=Llama-3.1-8B-Ins, Peak Mem (GB)=62.62, Step Time (s/step)=2.102026.0568.4447.6961.6982.0280.3954.5376.8
BaseModel=Llama-3.1-8B-Ins2026.0568.244.5460.4969.6779.4254.5677.5