Qwen / image-text-to-text updated 1 year ago

Qwen2-VL-2B-Instruct

We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.

Params
2.2 B
Context
32,768
Downloads 30d
3.0 M
Likes
518
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
3.1 M3.0 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 4.4 GB 5.7 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 32K ctx 4.4 GB 6.7 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
Qwen2VLForConditionalGeneration
Parameters
2.2 B
Tensor type
BF16
Context length
32,768
Vocabulary
151,936
Layers / heads
28 / 12
Licence
apache-2.0
First seen on the Hub
2024-08-28
Training datasets
undisclosed
Added to our catalog
2026-07-28