Qwen / image-text-to-text updated 5 months ago

Qwen3.5-4B

Name: Qwen3.5-4B
Author: Qwen

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

Params

4.7 B

Context

—

Downloads 30d

6.7 M

Likes

788

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

6.7 M6.2 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	9.3 GB	11.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Qwen3_5ForConditionalGeneration
Parameters: 4.7 B
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2026-02-27
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative Qwen3.5-4B-GGUF unsloth 1.2 M

Compare with

Qwen3.5-9B 12.4 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3-VL-8B-Instruct 4.9 M Qwen3-VL-4B-Instruct 4.0 M chandra-ocr-2 3.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB