unsloth

/

Qwen3-30B-A3B-bnb-4bit

Like 22

Follow

Unsloth AI 39.1k

I get this message, then it crashes:

WARNING 05-22 16:12:48 [utils.py:168] The model class Qwen3MoeForCausalLM has not defined `packed_modules_mapping`, this may lead to incorrect mapping of quantized or ignored modules

Did you try the unquantized version and see if it works? Unsure if vllm supports Bnb MOE models

If I could, I would xd

Are there other options?