# Qwen/Qwen3-VL-4B-Instruct

This model is a vision language model with native 256K context that can be expanded to 1M and handle books and hours long video with full recall. It also supports OCR in 32 languages and can judge object positions, viewpoints, and occlusions for spatial reasoning.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-qwen-qwen3-vl-4b-instruct
- Citation: Qwen/Qwen3-VL-4B-Instruct. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-qwen-qwen3-vl-4b-instruct (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: Vision
- Task: image-text-to-text
- Framework: transformers
- License: apache-2.0: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct
- Hosting: hosted (14 files)
- Files: 14 hosted of 14 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 14 hosted of 14 listed
- Full repo upstream: 8.89 GB
- Recommended file: 8.88 GB (2 files)
- Parameters: 4B
- Download: https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/download-plan)
- Per-file SHA-256: available for 14 of 14 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 4037454
- Stars: 428
- Card completeness: 89%

## Description

This model is a vision language model with native 256K context that can be expanded to 1M and handle books and hours long video with full recall. It also supports OCR in 32 languages and can judge object positions, viewpoints, and occlusions for spatial reasoning.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: image-text-to-text
- Library: transformers
- Task categories: image-text-to-text
- Paper ids: 2505.09388, 2502.13923, 2409.12191, 2308.12966
- File hints: 14 upstream file samples

## Referenced Data

- Paper: 2505.09388
- Paper: 2502.13923
- Paper: 2409.12191
- Paper: 2308.12966

## File Hints

- .gitattributes (1.5 KB)
- README.md (7.0 KB)
- chat_template.json (5.4 KB)
- config.json (1.5 KB)
- generation_config.json (269 B)
- merges.txt (1.6 MB)
- model-00001-of-00002.safetensors (4.6 GB) LFS
- model-00002-of-00002.safetensors (3.6 GB) LFS
- model.safetensors.index.json (63 KB)
- preprocessor_config.json (390 B)
- tokenizer.json (6.7 MB)
- tokenizer_config.json (11 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- Mirrored 6 selected Hugging Face files by configured-admin; hashes computed from downloaded bytes and manifest signed.
- External catalog metadata imported from Hugging Face public API on 2026-07-02T00:22:10.011Z.
- Open license detected as apache-2.0.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-qwen-qwen3-vl-4b-instruct
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-qwen-qwen3-vl-4b-instruct
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-qwen-qwen3-vl-4b-instruct&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen3-vl-4b-instruct/decentralized-fallbacks