Skip to content
Constructor
My neuronets
Registry
Spaces
Docs
FAQ
EN
▾
Testnet
▾
Sign in
Models
/
qwen3.6-35b-a3b
⧉
Q
Qwen3.6-35B-A3B
Alibaba / Qwen · Qwen3.6
Create a neuronet with this model →
LLM
Apache-2.0
public
Trusted
35B params
chat
moe
fast
MoE 35B with ~3B active: near-27B quality, much faster.
Model card
Spec & files
Deploy settings
MoE 35B with ~3B active: near-27B quality, much faster.
At a glance
Task:
LLM (InferenceV1)
Params:
35B
License:
Apache-2.0 (commercial use OK)
Hardware:
72 GB+ VRAM
dtype:
Bf16, Fp16