Qwen / Qwen3-VL 30B-A3B Thinking
BF16 quantization for Qwen3-VL 30B-A3B Thinking
The published profile is indicative; engineering measurements are completed for the selected model and hardware.
Before → After
Base releaseVerified checkpoint
30.500B
30.500B
QuantizationBF16
Quality retention target
Quality retention target
Production artifactArtifact
Lineage and benchmark report
Lineage and benchmark report
GPU targeting
Weights and KV cacheEstimated until measured during engineering
Estimated VRAMMeasured
Runtime packagingtransformers
Transparent pricing
Not currently orderable