CoolFace
Modelpublic

Neooooo/qf-integration-test

sourceHugging Faceupdated 7mo agoView on Hugging Face
0likes11downloads
Model Card

Neooooo/qf-integration-test

QuantForge Metadata

  • —Base model: Qwen/Qwen3-30B-A3B
  • —Quantization scheme: nvfp4
  • —Calibration dataset: HuggingFaceH4/ultrachat_200k
  • —Calibration samples: 32
  • —Max sequence length: 512
  • —Ignored layers: lm_head, re:.*\.mlp\.gate$, re:.*\.mlp\.router$

Accuracy (BF16 vs NVFP4)

TaskMetricBF16NVFP4Recovery
arc_challengeacc,none0.40000.30000.750
hellaswagacc,none0.40000.40001.000

Aggregate macro recovery: 0.875

Note: Scores estimated from subset.

Performance

Performance benchmark unavailable: evaluate.skipperf=true_

Usage (vLLM)

bash
vllm serve Neooooo/qf-integration-test