Qwen / image-text-to-text updated 6 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

6.9 M

Likes

941

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

Download history

daily snapshots · 55 days

▲ 752 K in the last 30 days (9.8%)

7.8 M6.2 M

Jul 28Aug 15Sep 2Sep 20

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 905 K Derivative Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Jackrong 309 K

Compare with any image-text-to-text model

Popular comparisons

Qwen3-VL-8B-Instruct 19.5 M Qwen3.5-9B 9.3 M Qwen2.5-VL-7B-Instruct 6.9 M Qwen3.8-27B-MLX-4bit 4.7 M Qwen3.8-27B-MLX-5bit 4.5 M Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 4.0 M