YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Performance Summary: Qwen3-30B-A3B REAP and FP8-DYNAMIC RTN Ablations Study

Overview

This report compares 4 compressed/quantized variants of Qwen3-30B-A3B-Instruct-2507 against the unquantized baseline across 5 evaluation benchmarks.

  • FP8-DYNAMIC: Quantized with FP8-DYNAMIC RTN only
  • REAP-25pct: Compressed with REAP (25% sparsity) only
  • FP8-DYNAMIC + REAP-25pct: Quantized with FP8-DYNAMIC RTN first, then compressed with REAP (25% sparsity)
  • REAP-25pct + FP8-DYNAMIC: Compressed with REAP (25% sparsity) first, then quantized with FP8-DYNAMIC RTN

Important Note: The baseline model was served with tp=2 across 2 GPUs, so its server statistics may appear different from the single-GPU variants. The baseline model size (57 GB) is accurate, but its KV cache size and token capacity may be inflated relative to a single-GPU deployment.

Model Configurations

Configuration Model Size Size Reduction Session ID
Baseline (Unquantized) 57.00 GB — 07102026028
FP8-DYNAMIC 29.21 GB 48.8% 07102026-f817
REAP-25pct 43.43 GB 23.8% 07102026-aedc
FP8-DYNAMIC + REAP-25pct 22.43 GB 60.6% 07102026-da72
REAP-25pct + FP8-DYNAMIC 22.43 GB 60.6% 07102026-05ea

Accuracy Scores

Task Baseline FP8-DYNAMIC REAP-25pct FP8-DYNAMIC + REAP-25pct REAP-25pct + FP8-DYNAMIC
gsm8k_platinum_cot_llama 0.9680 0.9763 0.9586 0.9573 0.9570
ifeval 0.8945 0.8921 0.8705 0.8733 0.8713
math_500|0 0.8887 0.8913 0.8893 0.8740 0.8813
mmlu_cot_llama 0.8422 0.8397 0.7930 0.7910 0.7921
mmlu_pro_chat 0.7881 0.7848 0.7264 0.7237 0.7253
Average 0.8763 0.8768 0.8476 0.8439 0.8454

Accuracy Recovery vs. Baseline

Task FP8-DYNAMIC REAP-25pct FP8-DYNAMIC + REAP-25pct REAP-25pct + FP8-DYNAMIC
gsm8k_platinum_cot_llama 100.86% (+0.0083) 99.03% (-0.0094) 98.89% (-0.0107) 98.86% (-0.0110)
ifeval 99.73% (-0.0024) 97.32% (-0.0240) 97.63% (-0.0212) 97.41% (-0.0232)
math_500|0 100.29% (+0.0026) 100.07% (+0.0006) 98.35% (-0.0147) 99.17% (-0.0074)
mmlu_cot_llama 99.70% (-0.0025) 94.16% (-0.0492) 93.92% (-0.0512) 94.05% (-0.0501)
mmlu_pro_chat 99.58% (-0.0033) 92.17% (-0.0617) 91.83% (-0.0644) 92.03% (-0.0628)
Average 100.06% (+0.0005) 96.72% (-0.0287) 96.30% (-0.0324) 96.47% (-0.0309)

Variant Ranking (by Average Recovery)

Rank Configuration Avg Recovery Avg Δ
1 FP8-DYNAMIC 100.06% +0.0005
2 REAP-25pct 96.72% -0.0287
3 REAP-25pct + FP8-DYNAMIC 96.47% -0.0309
4 FP8-DYNAMIC + REAP-25pct 96.30% -0.0324

Resource Utilization

Metric Baseline FP8-DYNAMIC REAP-25pct FP8-DYNAMIC + REAP-25pct REAP-25pct + FP8-DYNAMIC
KV Cache Size (GB) 40.29* 39.90 25.86 46.57 46.57
KV Cache Tokens 880,192* 435,776 282,448 508,672 508,672
Recommended Concurrency 27.51* 13.62 8.83 15.90 15.90

* Baseline was served with tp=2 across 2 GPUs; KV cache size and token capacity are inflated relative to single-GPU variants and should not be directly compared.

Concurrency Issues

Configuration Task Issues
REAP-25pct mmlu_pro_chat max KV cache: 91.2%

Evaluation Date: 2026-07-10 vLLM Version: 0.24.0 Max Model Length: 32,000 tokens Source PRs: #37, #38, #39, #40, #41

Downloads last month
90
Safetensors
Model size
23B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support