Qwen3-1.7B-GLB-3D-Coder

Try Try

Qwen3-1.7B-GLB-3D-Coder has 1.72B parameters (1.72B active per token) and takes 3.44 GB on disk. See where its parameters live, layer by layer, and what hardware it needs.

At a glance

ccore/Qwen3-1.7B-GLB-3D-Coder
Repo createdNov 11, 2026updated Nov 13, 2026
Model typeDenseFull attention (GQA)
InputsText
Total parameters1.72B
Active per token1.72B100% of the model
ExpertsNone (dense)
Max context (from config)40K tokens
Layers28
On disk3.44 GB1 file
PrecisionFP16 (100%)
QuantizationNoneoriginal precision (FP16)
Fewest GPUs1× RTX 4060a single 8 GB card · weights only
FamilyQuantization of Qwen/Qwen3-1.7B
Licenseapache-2.0
GitHubNot linked