Qwen3.5-4B-Qwen3.8-27B-Draft

Try Try

Qwen3.5-4B-Qwen3.8-27B-Draft has 4.21B parameters (4.21B active per token) and takes 8.41 GB on disk. See where its parameters live, layer by layer, and what hardware it needs.

At a glance

nvidia/Qwen3.5-4B-Qwen3.8-27B-Draft
Repo createdNov 11, 2026updated Nov 17, 2026
Model typeDenseHybrid attention: 24 linear + 8 full (GQA)
InputsText
Total parameters4.21B
Active per token4.21B100% of the model
ExpertsNone (dense)
Max context (from config)256K tokens
Layers3224 linear + 8 full attention
On disk8.41 GB1 file
PrecisionBF16 (100%)
QuantizationNoneoriginal precision (BF16)
Fewest GPUs1× RTX 3060 12 GBa single 12 GB card · weights only
FamilyFine-tune of Qwen/Qwen3.5-4B
Licensenvidia-open-model-agreement (custom)
GitHubNot linked