llamaperf

Qwen2.5 7B

on NVIDIA RTX 5090 · vLLM

NVIDIA hardware
Jun 4, 2026
VRAM reported
32 GB

Summary

User benchmarks abliteration tools Apostate, Huihui and Heretic on Qwen 2.5 7B on an RTX 5090 32GB. Setup is vLLM 0.19.0 in bf16, evaluated with lm-evaluation-harness. The run reports MMLU, GSM8K, HellaSwag, ARC Challenge, WinoGrande, TruthfulQA MC2, PiQA, LAMBADA ppl, HarmBench ASR and KL divergence. No tokens/sec is reported.