Modelpublic

minjaechoi/qwen36-35b-a3b-2p00bit-r12

sourceHugging Faceupdated 10d agoView on Hugging Face

0likes150downloads

Model Card

Qwen3.6-35B-A3B — 2.00-bit routed experts (r12)

Internal research checkpoint. Routed experts average 2.00 bits; every other weight is BF16. Weights are stored dequantized in BF16 tensors and load with stock transformers / vLLM.


Base model	Qwen/Qwen3.6-35B-A3B
Routed-expert average	2.00 bits
Internal ID	r12

License follows the base model.