Is this issue fixed ?
I am getting the same error

for this

import torch
from transformers import (
    pipeline,
    BitsAndBytesConfig,
)

# 1) Build your 4-bit config.
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    llm_int8_enable_fp32_cpu_offload=True,   # keeps some weights in FP32 on CPU
    bnb_4bit_quant_type="nf4",              # or "fp4", "fp4-dq", etc.
    bnb_4bit_compute_dtype=torch.float16,    # compute in fp16 on GPU
)

# 2) Create the pipeline, passing quantization_config:
pipe = pipeline(
    "image-text-to-text",
    model="unsloth/gemma-3-27b-it-unsloth-bnb-4bit",
    cache_dir="/mnt/models/gemma3",
    trust_remote_code=True,
    device_map="auto",
    quantization_config=bnb_config,            # ← here’s the key
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://…/candy.JPG"},
            {"type": "text",  "text": "What animal is on the candy?"}
        ]
    },
]

print(pipe(text=messages))