---
license: apache-2.0
base_model: Qwen/Qwen3.5-2B
pipeline_tag: text-generation
tags:
- qwen
- gguf
- quantized
- voco
---

# qwen3.5-2b-q4_k_m-GGUF

GGUF-converted and quantized derivative of Alibaba's Qwen3.5 2B for on-device inference.

## Base Model
- **Model**: Qwen3.5 2B
- **Provider**: Alibaba (Qwen Team)
- **Source**: https://huggingface.co/Qwen/Qwen3.5-2B
- **License**: Apache 2.0

## Conversion Details
- **Converter**: llama.cpp convert_hf_to_gguf.py (upstream master, May 2026)
- **Quantization**: Q4_K_M
- **GGUF Size**: ~1.3 GB
- **Converted by**: Zanish Labs / Voco

## Runtime
- Compatible with llama.cpp (CPU/NEON)
- Tested on Voco iOS app (STQ1_0 backend, PR #22836)

## Attribution
This is a converted/quantized derivative. The original model was created by Alibaba's Qwen Team and is licensed under Apache 2.0. See LICENSE file.

## Links
- Original model: https://huggingface.co/Qwen/Qwen3.5-2B
- llama.cpp: https://github.com/ggml-org/llama.cpp