Modelpublic

minjaechoi/qwen36-35b-a3b-2p36bit-r14

sourceHugging Faceupdated 9d agoView on Hugging Face

0likes391downloads

Model Card

Qwen3.6-35B-A3B — 2.358-bit routed experts (r14)

Internal research checkpoint. Routed experts average 2.358 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	2.358 bits
Internal ID	r14

License follows the base model.