---
license: apache-2.0
base_model: Qwen/Qwen3.5-2B
tags:
  - tflite
  - on-device
  - qwen
  - mobile
  - gated-deltanet
---

# Qwen 3.5 2B — TFLite (.tflite)

Qwen 3.5 2B as raw TFLite format for on-device inference with the TFLite Interpreter API.

> **For LiteRT-LM Engine usage, use the bundled version instead: [paulsp94/Qwen3.5-2B-LiteRT-LM](https://huggingface.co/paulsp94/Qwen3.5-2B-LiteRT-LM)**

## What's this

Raw `.tflite` model file — use this if you're building your own inference pipeline with the TFLite Interpreter API directly. If you want the ready-to-use LiteRT-LM bundle with tokenizer included, use the [LiteRT-LM version](https://huggingface.co/paulsp94/Qwen3.5-2B-LiteRT-LM) instead.

## Architecture

| | |
|---|---|
| **Base model** | [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) |
| **Layers** | 24 total: 18× GatedDeltaNet linear + 6× GQA full attention |
| **Quantization** | int8 dynamic |
| **Format** | TFLite (.tflite) |
| **Size** | ~1.9 GB |

## Files

- `qwen35_2b.tflite` — The converted model
- `tokenizer.json` — BPE tokenizer (you'll need to handle tokenization yourself)
- `tokenizer_config.json` — Tokenizer configuration
- `config.json` — Original model config

## Conversion

Source: [allot/tools/model-export](https://github.com/paulsp94/allot/tree/main/tools/model-export)