Downloads · 30 days
56
7% of all-time downloads
Qwen3.5-2B-TFLite
paulsp94/Qwen3.5-2B-TFLite
Qwen3.5-2B-TFLite is a machine learning model from paulsp94. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen 3.5 2B as raw TFLite format for on-device inference with the TFLite Interpreter API.
All-time downloads
812
Public
Repo size
4.9 GB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.tflite3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3_5
- Access
- Public
- Created
- Mar 17, 2026
- Updated
- Mar 18, 2026
- SHA
- b3dc1306
Base models
Model card
From the Hugging Face model README
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
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 instead.
Architecture
| Base model | 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 modeltokenizer.json— BPE tokenizer (you'll need to handle tokenization yourself)tokenizer_config.json— Tokenizer configurationconfig.json— Original model config
Conversion
Source: allot/tools/model-export
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Mar 17, 2026
- Updated
- Mar 18, 2026