Qwen3-VL-30B-A3B-Instruct — GBLM-Pruner (50% Unstructured Sparsity)
Created with GBLM-Pruner using 128 C4 training windows of 2048 tokens (seed 0).
Method: GBLM-Pruner. Measured decoder-matrix sparsity: 50.00000000%.
The vision encoder, MoE routers, embeddings, normalization and output head remain dense.
See pruning_report.json for the exact scope, counts and environment.
GBLM uses the repository's additive activation-plus-absolute-gradient metric (summed L1 gradients scaled by 100).
This is zero-weight pruning: tensor shapes and dense file sizes are unchanged.
RealWorldQA evaluation is run separately; no accuracy claim is made until it completes.
from transformers import AutoProcessor, Qwen3VLMoeForConditionalGeneration
path = "CompressedMichael/Qwen3-VL-30B-A3B-Instruct-GBLM-Pruner-50pct"
processor = AutoProcessor.from_pretrained(path)
model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
path, dtype="auto", device_map="auto", attn_implementation="sdpa")
The weights use native Transformers tensor names and require no custom modeling files.
Prepared with Transformers 4.57.6. The base model is licensed under Apache 2.0.