Qwen2.5-VL-3B-Instruct-AWQ
--- licensename: qwen-research licenselink: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct-AWQ/blob/main/LICENSE language: - en pipelinetag: image-text-to-text tags: - multimodal libraryname: transformers basemodel: - Qwen/Qwen2.5-VL-3B-Instruct ---
Params
3.8 B
Context
128,000
Downloads 30d
868 K
Likes
78
Download history
daily snapshots · 9 days869 K867 K
Nov 2Nov 5Nov 8Nov 10
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 | i32 | 3.4 GB | 4.8 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 125K ctx | 3.4 GB | 13.0 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
- Qwen2_5_VLForConditionalGeneration
- Parameters
- 3.8 B
- Tensor type
- I32
- Context length
- 128,000
- Vocabulary
- 151,936
- Layers / heads
- 36 / 16
- First seen on the Hub
- 2025-02-13
- Base model
- Qwen2.5-VL-3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-02
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model