List your company

Inference Throughput on ISL 8192 OSL 16384 workload

224Max Batch SizeNano v3 12BA2A
28.4879.24130180.76May 8, 2026

Evaluation results

MethodLinks
Nano v3 12BA2AISL/OSL=8192/16384, Hardware=H100 GPU, Precision=bfloat16, Framework=vLLM2026.052242.4
Nano v3 23BA2.8AISL/OSL=8192/16384, Hardware=H100 GPU, Precision=bfloat16, Framework=vLLM2026.051081.8
Nano v3 30BA3.6AISL/OSL=8192/16384, Hardware=H100 GPU, Precision=bfloat16, Framework=vLLM2026.05361