Yoursmiling/Qwen3.5-4B-LiteRT

qwen3.5-4b local multimodal conversion

This repository contains a locally converted Qwen3.5 multimodal LiteRT package.

Locally converted Qwen3.5 4B multimodal LiteRT package with split vision/text components.

• target: qwen3.5-4b
• artifact: model_multimodal.litertlm
• size: 5019.62 MB
• generated_at: 2026-04-04T12:43:24.035354+00:00

Package Contents

• model_multimodal.litertlm
• tokenizer.json
• tokenizer_config.json
• chat_template.jinja
• vision_encoder_quantized.tflite
• vision_adapter_quantized.tflite
• embedder_quantized.tflite
• model_quantized.tflite
• model_multimodal_llm_metadata_multimodal.pb
• model_multimodal_export_summary.json

Notes

Validated with split-component coverage checks and runtime smoke execution.