# Qwen3-VL-4B-Instruct (slim)

> Qwen3-VL-4B-Instruct is Alibaba's open-weight dense vision-language model of about 4B parameters, taking text, images and video with a 262,144-token context, published on Hugging Face in BF16, FP8 and GGUF under Apache 2.0.

- Full: https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct.md (~12,500 tokens) · this version ~2,030 tokens · JSON https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct.json · canonical https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21 · pricing https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct#pricing · reviews https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**D · 52.6/100 · rank #84 of 100 open-weight models · #68 in Open-weight models · not agent-ready · confidence high**


Assessment: A small vision-language cousin for reading screenshots, documents, charts and video, running in about 3.5 GB from Alibaba's Q4_K_M GGUF in every major runtime under plain Apache 2.0. It has no thinking mode, and Qwen hasn't answered repository questions or published safety work, so add your own guardrails before letting it drive a GUI.

## Facts

- Kind: Open-weight model · vendor: Alibaba (Qwen team) · category: Open-weight models · legal entity: Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder) · provenance 49/100
- Packages: huggingface `Qwen/Qwen3-VL-4B-Instruct`, huggingface `Qwen/Qwen3-VL-4B-Instruct-FP8`, huggingface `Qwen/Qwen3-VL-4B-Instruct-GGUF`, ollama `qwen3-vl:4b-instruct`
- Auth: None · pricing: Free · x402: no · licence: Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The open weights at huggingface.co/Qwen/Qwen3-VL-4B-Instruct and Alibaba's FP8 and GGUF repositories, read from the model cards, the files and their metadata, the chat template, the QwenLM/Qwen3-VL GitHub repository, the Qwen3-VL technical report and the runtimes' own code on 21 October 2026. Nothing was downloaded or run. The Thinking edition is a separate repository and isn't graded here
- Model: 4,437,815,808 parameters in BF16 per the files' metadata, a 36-layer Qwen3 language model with tied input and output embeddings and a 24-layer vision encoder, Interleaved-MRoPE and DeepStack. Text, images and video in, text out
- Files: Two safetensors shards in BF16 (8.89 GB in the repository) with chat_template.json, a separate FP8 repository (6.04 GB, two shards) and a GGUF repository with F16, Q8_0 and Q4_K_M language files and F16 and Q8_0 vision files. No pickle files and no Python code. Hugging Face lists a SHA-256 for every large file. No LICENSE file in the weights repositories; the licence is in the cards' metadata and in the GitHub repository. The GGUF card, unlike the 2B and 32B ones, has no instructions for running it
- Licence: Apache 2.0. No acceptable use policy in the repositories
- Runtimes: Model code in Transformers (qwen3_vl, in 4.57.0), vLLM (0.11.0 or later per Qwen's README), SGLang (qwen3_vl, in 0.5.3 and later), the qwen3vl architecture in llama.cpp with its multimodal tools, and qwen3-vl:4b-instruct in Ollama's library
- Context: 262,144 tokens native per the config and card. The card and the GitHub README say it extends to about 1,000,000 with YaRN
- Tools and reasoning: The chat template declares tools as JSON in `<tools>` and expects one or more calls as JSON objects inside `<tool_call>` tags, with results returned in `<tool_response>`. Qwen's cookbooks parse the tags by hand; SGLang's cookbook names its `qwen` parser. The card doesn't describe tool calling. This Instruct edition has no thinking mode; thinking is in the separate Thinking edition
- Hardware: The card states no memory needs. File sizes are 8.89 GB in BF16, 6.04 GB in FP8 and 2.5 GB for the Q4_K_M GGUF plus its 0.45 GB Q8_0 vision file
- Training data: Not described on the card. The technical report names data categories and open-source sources, token budgets per stage and the filtering, with no knowledge cut-off

- Scores: Capability 25, Reach 95, Risk 55, Agent interface 60, Documentation and upkeep 31 · total over the 7 assessed categories
- Why: Capability, From 10 independent benchmark results in 6 areas, each scored as its share of the way from the benchmark's floor to the best result any mode… · Reach, Alibaba's own Q4_K_M GGUF with its vision file is 2.95 GB, so with a fifth added it needs about 3.5 GB and fits well within 16 GB (30). · Risk, Safetensors and GGUF only and no code in the repositories, so the FP8 card's trust_remote_code flag runs nothing (25). · Agent interface, A Jinja chat template in the repository (20). · Documentation and upkeep, The card misses limitations, languages and a cut-off (11).
- Sources: 20, open questions: 4, both in the full twin
- Capabilities: model.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/qwen3-vl-4b-instruct.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/qwen3-vl-4b-instruct.svg` or a link to https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct from a page on qwen.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Start it with `llama-server -hf Qwen/Qwen3-VL-4B-Instruct-GGUF:Q4_K_M --jinja -c 32768`, or `ollama run qwen3-vl:4b-instruct`
2. In Ollama the plain `qwen3-vl:4b` tag is the Thinking edition, so name `4b-instruct`
3. With the GGUF, load the mmproj vision file too, or images won't be read
4. Parse tool calls as JSON inside `<tool_call>` tags, or use SGLang's `--tool-call-parser qwen`
5. Use the card's sampling, `temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5` for vision and `temperature=1.0, top_p=1.0, top_k=40, presence_penalty=2.0` for text
6. Validate JSON output yourself, since structured output isn't documented
7. vLLM needs 0.11.0 or later and Transformers 4.57.0 or later

## Connect

```bash
ollama run qwen3-vl:4b-instruct
# or with vLLM 0.11.0 or later, per Qwen's README:
vllm serve Qwen/Qwen3-VL-4B-Instruct-FP8
# or with SGLang, using the tool parser its cookbook names for Qwen3-VL:
python -m sglang.launch_server --model-path Qwen/Qwen3-VL-4B-Instruct --tool-call-parser qwen
```

```bash
curl http://localhost:11434/api/chat \
  -d '{"model": "qwen3-vl:4b-instruct", "messages": [{"role": "user", "content": "Hello!"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Qwen3-Embedding-8B | BB | 74.7 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-8b.min.md |
| Gemma 4 31B IT | BB | 74.1 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-31b-it.min.md |
| Qwen3-Embedding-4B | BB | 72.9 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md |
| Gemma 4 26B A4B IT | BB | 72.2 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.min.md |
| Gemma 4 12B IT | BB | 71.3 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-12b-it.min.md |


## Panel reviews (4, average 2.8/5, desk reviews from public material, no calls made)

- ★★☆☆☆ Two loading reports without a reply (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★★ 2.95 GB with vision, FP8 at 6.04 GB (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Small vision model with near-zero terminal results (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Screen control at 4B, no injection guidance (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-21; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with ratings from 2 to 5. They agree the files are clean and hashed under Apache 2.0, that the tool format is the family's template-only one, and that Qwen hasn't answered 14 discussions or two loading reports. Read it as a 2.95 GB vision model with Alibaba's own FP8 and GGUF builds, weak terminal and agent results and no guidance for the screen control the card sells.