qwen3-vl-4b-thinking (Keras 3, bf16)

Pure-Keras 3 conversion of Qwen/Qwen3-VL-4B-Thinking for kerasformers. Apache 2.0.

This repo holds the converted model weights and tokenizer.json.

from kerasformers.models.qwen3_vl import Qwen3VLGenerate, Qwen3VLProcessor
model = Qwen3VLGenerate.from_weights("qwen3-vl-4b-thinking")
processor = Qwen3VLProcessor.from_weights("qwen3-vl-4b-thinking")

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for KerasFormers/qwen3-vl-4b-thinking

Base model

Qwen/Qwen3-VL-4B-Thinking

Finetuned

(28)

this model