Head to head · Open-weight models you run yourself · October 2026 research run
Qwen3.5-4B vs WeVisOne-VL-4B
Qwen3.5-4B and WeVisOne-VL-4B score within a point of each other on agent readiness, 61.2 (C) and 61 (C). WeVisOne-VL-4B leads on documentation and upkeep. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons
Which one, for what
Best for Agents that want a cheap local helper for tool calls, short reasoning and reading images on a laptop or small GPU
Ahead on
- Reach, 85 against 70
Watch for
No quantised build from Alibaba for this size
Best for Agents that need to locate, count or cut out objects in images on a small GPU, under a permissive licence
Ahead on
- Documentation and upkeep, 48 against 34
Watch for
The pixel decoder ships as a pickle file
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reach Qwen3.5-4B +15
Qwen3.5-4B 85
Memory earns the full 30 because Ollama's own Q4_K_M build is 3.3 GB, about 4 GB with the fifth added, though Alibaba itself publishes no quantised 4B, so builds scores 0. Runtimes reach the 25 cap on vLLM's stable release, Transformers 5.2.0, llama.cpp, Ollama's library and LM Studio's catalogue. Apache 2.0 with nothing added gives the full 15 for terms, the ungated repository the full 10 for download, and two providers (featherless-ai, live on Hugging Face on 2 November, and Doubleword's own list per the 21 October check) the 5 for hosted too. 30 + 25 + 0 + 15 + 10 + 5 = 85.
WeVisOne-VL-4B 70
Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 9.7 GB, and 9.7 GB × 1.2 = 11.6 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen3VLForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors file, three at 5 each. Builds 0, Tencent publishes the BF16 weights only. Terms 15, Apache 2.0 in the card's metadata with the LICENSE file in the repository, and nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 30 + 15 + 0 + 15 + 10 + 0 = 70.
Documentation and upkeep WeVisOne-VL-4B +14
Qwen3.5-4B 34
The card covers five of the seven items and misses limitations and a cut-off (14). Training data is a general description without a cut-off (5). The files last changed on 2 March 2026, 245 days before 2 November, which is within a year (5). No Qwen member has answered any of the 21 discussions that aren't pull requests, four of them opened since 21 October (0), and the GitHub issues couldn't be counted. Earlier 4B models stay in their own repositories without dated notes (5), and two pull requests fixing the template and adding generation_config.json wait unanswered (5). 14 + 5 + 5 + 0 + 5 + 5 = 34.
WeVisOne-VL-4B 48
Model card 8, Intended use, limitations and the architecture are on the card. Training data 5, A general description in the README of a data engine and over 100 million annotated images, with no sources named and no cut-off. Last change 20, the last commit, on 27 October 2026, added links to the paper and project page, 14 days before this check. Responsiveness 0, Neither of the 2 discussions that aren't pull requests (23 and 26 October 2026) has a reply from a tencent member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, 14 days old. File health 10, Config, template and card agree on the Qwen3-VL classes, and the card names mask_decoder.pt as required and it's there. 8 + 5 + 20 + 0 + 5 + 10 = 48.
Score by category
| Category | Weight this run | Qwen3.5-4B | WeVisOne-VL-4B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 85 | 70 | Qwen3.5-4B +15 |
| Risk | 20%20 | 55 | 55 | even |
| Agent interface | 10%10 | 70 | 70 | even |
| Documentation and upkeep | 10%10 | 34 | 48 | WeVisOne-VL-4B +14 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61.2/100 | C 61/100 |
Facts side by side
| Fact | Qwen3.5-4B | WeVisOne-VL-4B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Alibaba (Qwen team) | Tencent (WeChat Vision) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-03-02 | 2026-10-27 |
| Terms last updated | no document linked | not read yet |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 3/5 (4) | none |
Verdicts
Qwen3.5-4B
A small vision-language cousin for tool calls, light agent steps and image or video reading on almost any machine, with switchable thinking. Ollama's 3.3 GB build or the 9.3 GB BF16 files run in every major runtime under plain Apache 2.0. The main risks are no safety results, no structured-output guarantee and no answers from Alibaba since March.
WeVisOne-VL-4B
A small Apache 2.0 perception model that finds, counts, reads and cuts out what you name in an image, and says None when it isn't there. Boxes and points run in vLLM, SGLang or Transformers. Masks and mattes need Tencent's package and a pickle file. Two weeks old, with no questions answered yet and no safety results.
Before you call either
Qwen3.5-4B
- Smallest start is
ollama run qwen3.5:4b(Q4_K_M, about 4 GB with context) - Full precision
vllm serve Qwen/Qwen3.5-4B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder - Turn thinking off with
"chat_template_kwargs": {"enable_thinking": false}in the request body, since it's on by default and/thinkand/nothinkaren't supported - There's no generation_config.json, so pass the card's sampling yourself, for example
temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5without thinking - Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
- Validate any JSON it returns, since structured output isn't documented
WeVisOne-VL-4B
- Use Tencent's package:
WeVisOneVL("tencent/WeVisOne-VL-4B", backend="vllm")thenmodel.predict(image, task=..., query=...) - Tasks are detection, referring, point, count_box, count_point, ocr, ocr_grounding, segmentation and matting
- A None answer means the target isn't in the image. Treat it as a result, not an error
- mask_decoder.pt is a pickle. Load it only from the tencent repository, and check its SHA-256 against the Hub's
- Send one image a turn. Video grids are rejected by the decoder
- The card says it isn't for identifying individuals or for high-impact decisions on its own
Questions
Which is better for AI agents, Qwen3.5-4B or WeVisOne-VL-4B?
Qwen3.5-4B and WeVisOne-VL-4B score within a point of each other on agent readiness, 61.2 (C) and 61 (C). WeVisOne-VL-4B leads on documentation and upkeep.
Other comparisons with Qwen3.5-4B or WeVisOne-VL-4B
- Agents-A1-4B vs Qwen3.5-4B
- Agents-A1-4B vs WeVisOne-VL-4B
- Apertus v1.5 8B vs Qwen3.5-4B
- Apertus v1.5 8B vs WeVisOne-VL-4B
- Apodex-1.1-mini vs Qwen3.5-4B
- Apodex-1.1-mini vs WeVisOne-VL-4B
- Arete-27B vs Qwen3.5-4B
- Arete-27B vs WeVisOne-VL-4B
- BigBang-v1 vs Qwen3.5-4B
- BigBang-v1 vs WeVisOne-VL-4B
- Carbon-X vs Qwen3.5-4B
- Carbon-X vs WeVisOne-VL-4B
- Cola2 vs Qwen3.5-4B
- Cola2 vs WeVisOne-VL-4B
- Cosmos-Reason2-2B vs Qwen3.5-4B
- Cosmos-Reason2-2B vs WeVisOne-VL-4B
- Darwin-36B-Opus vs Qwen3.5-4B
- Darwin-36B-Opus vs WeVisOne-VL-4B
- DeepSeek-V3.2 vs Qwen3.5-4B
- DeepSeek-V3.2 vs WeVisOne-VL-4B
- DeepSeek V4.1 Flash vs Qwen3.5-4B
- DeepSeek V4.1 Flash vs WeVisOne-VL-4B
- DeepSeek-V4-Flash-0731 vs Qwen3.5-4B
- DeepSeek-V4-Flash-0731 vs WeVisOne-VL-4B
- Devstral Small 2 vs Qwen3.5-4B
- Devstral Small 2 vs WeVisOne-VL-4B
- DiffusionGemma 26B A4B IT vs Qwen3.5-4B
- DiffusionGemma 26B A4B IT vs WeVisOne-VL-4B
- EXAONE 4.5 33B vs Qwen3.5-4B
- EXAONE 4.5 33B vs WeVisOne-VL-4B
- Gemma 4 12B IT vs Qwen3.5-4B
- Gemma 4 12B IT vs WeVisOne-VL-4B
- Gemma 4 26B A4B IT vs Qwen3.5-4B
- Gemma 4 26B A4B IT vs WeVisOne-VL-4B
- Gemma 4 31B IT vs Qwen3.5-4B
- Gemma 4 31B IT vs WeVisOne-VL-4B
- Gemma 4 E2B IT vs Qwen3.5-4B
- Gemma 4 E2B IT vs WeVisOne-VL-4B
- Gemma 4 E4B IT vs Qwen3.5-4B
- Gemma 4 E4B IT vs WeVisOne-VL-4B
- GLM-4.5-Air vs Qwen3.5-4B
- GLM-4.5-Air vs WeVisOne-VL-4B
- GLM-4.7-Flash vs Qwen3.5-4B
- GLM-4.7-Flash vs WeVisOne-VL-4B
- GLM-5.3-Flash vs Qwen3.5-4B
- GLM-5.3-Flash vs WeVisOne-VL-4B
- GLM-5.3 vs Qwen3.5-4B
- GLM-5.3 vs WeVisOne-VL-4B
- gpt-oss-120b vs Qwen3.5-4B
- gpt-oss-120b vs WeVisOne-VL-4B
- gpt-oss-20b vs Qwen3.5-4B
- gpt-oss-20b vs WeVisOne-VL-4B
- Granite 4.2 30B vs Qwen3.5-4B
- Granite 4.2 30B vs WeVisOne-VL-4B
- Granite 4.2 3B vs Qwen3.5-4B
- Granite 4.2 3B vs WeVisOne-VL-4B
- Granite 4.2 8B vs Qwen3.5-4B
- Granite 4.2 8B vs WeVisOne-VL-4B
- Hy-Memory-30B-A3B vs Qwen3.5-4B
- Hy-Memory-30B-A3B vs WeVisOne-VL-4B
- Hy3 vs Qwen3.5-4B
- Hy3 vs WeVisOne-VL-4B
- Inkling-Small vs Qwen3.5-4B
- Inkling-Small vs WeVisOne-VL-4B
- Inkling vs Qwen3.5-4B
- Inkling vs WeVisOne-VL-4B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-4B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs WeVisOne-VL-4B
- Kimi K3.1 Pro vs Qwen3.5-4B
- Kimi K3.1 Pro vs WeVisOne-VL-4B
- Kimi K3 vs Qwen3.5-4B
- Kimi K3 vs WeVisOne-VL-4B
- Kolibri-1 vs Qwen3.5-4B
- Kolibri-1 vs WeVisOne-VL-4B
- Kronos vs Qwen3.5-4B
- Kronos vs WeVisOne-VL-4B
- Laguna M.1 vs Qwen3.5-4B
- Laguna M.1 vs WeVisOne-VL-4B
- Laguna S 2.1 vs Qwen3.5-4B
- Laguna S 2.1 vs WeVisOne-VL-4B
- Laguna XS 2.1 vs Qwen3.5-4B
- Laguna XS 2.1 vs WeVisOne-VL-4B
- LBS-27B vs Qwen3.5-4B
- LBS-27B vs WeVisOne-VL-4B
- LFM2.5-2.6B vs Qwen3.5-4B
- LFM2.5-2.6B vs WeVisOne-VL-4B
- LFM3-1.7B vs Qwen3.5-4B
- LFM3-1.7B vs WeVisOne-VL-4B
- LFM3-Audio-2B vs Qwen3.5-4B
- LFM3-Audio-2B vs WeVisOne-VL-4B
- LFM3-Omni-2B vs Qwen3.5-4B
- LFM3-Omni-2B vs WeVisOne-VL-4B
- LFM3-VL-2B vs Qwen3.5-4B
- LFM3-VL-2B vs WeVisOne-VL-4B
- Ling-3.0-tiny vs Qwen3.5-4B
- Ling-3.0-tiny vs WeVisOne-VL-4B
- Ling-3.1-flash-1019 vs Qwen3.5-4B
- Ling-3.1-flash-1019 vs WeVisOne-VL-4B
- LongCat-2.5 vs Qwen3.5-4B
- LongCat-2.5 vs WeVisOne-VL-4B
- MiMo-V2.6 Distill Qwen 9B vs Qwen3.5-4B
- MiMo-V2.6 Distill Qwen 9B vs WeVisOne-VL-4B
- MiMo-V2.6-Flash-RL vs Qwen3.5-4B
- MiMo-V2.6-Flash-RL vs WeVisOne-VL-4B
- MiniCPM-o 4.5 vs Qwen3.5-4B
- MiniCPM-o 4.5 vs WeVisOne-VL-4B
- MiniCPM-V 4.7 1B vs Qwen3.5-4B
- MiniCPM-V 4.7 1B vs WeVisOne-VL-4B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-4B
- MiniCPM-V 4.7 35B-A3B vs WeVisOne-VL-4B
- MiniCPM5-2B vs Qwen3.5-4B
- MiniCPM5-2B vs WeVisOne-VL-4B
- MiniMax-M2.5 vs Qwen3.5-4B
- MiniMax-M2.5 vs WeVisOne-VL-4B
- MiniMax-M2.7 vs Qwen3.5-4B
- MiniMax-M2.7 vs WeVisOne-VL-4B
- MiniMax-M3.1-Flash vs Qwen3.5-4B
- MiniMax-M3.1-Flash vs WeVisOne-VL-4B
- Mistral Large 4 vs Qwen3.5-4B
- Mistral Large 4 vs WeVisOne-VL-4B
- Muse Glimmer 30B vs Qwen3.5-4B
- Muse Glimmer 30B vs WeVisOne-VL-4B
- Nanbeige4.2-3B vs Qwen3.5-4B
- Nanbeige4.2-3B vs WeVisOne-VL-4B
- Nanbeige4.3-33B vs Qwen3.5-4B
- Nanbeige4.3-33B vs WeVisOne-VL-4B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Qwen3.5-4B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs WeVisOne-VL-4B
- Nemotron 3.5 Lightning 30B A3B vs Qwen3.5-4B
- Nemotron 3.5 Lightning 30B A3B vs WeVisOne-VL-4B
- Nemotron 3 Nano 30B A3B vs Qwen3.5-4B
- Nemotron 3 Nano 30B A3B vs WeVisOne-VL-4B
- Nemotron 3 Nano 4B vs Qwen3.5-4B
- Nemotron 3 Nano 4B vs WeVisOne-VL-4B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Qwen3.5-4B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs WeVisOne-VL-4B
- Nemotron 3 Super 120B A12B vs Qwen3.5-4B
- Nemotron 3 Super 120B A12B vs WeVisOne-VL-4B
- Nemotron 3 Ultra 550B A55B vs Qwen3.5-4B
- Nemotron 3 Ultra 550B A55B vs WeVisOne-VL-4B
- North Mini Code 1.0 vs Qwen3.5-4B
- North Mini Code 1.0 vs WeVisOne-VL-4B
- occamy-1.0 vs Qwen3.5-4B
- occamy-1.0 vs WeVisOne-VL-4B
- Olmo 3 7B Think vs Qwen3.5-4B
- Olmo 3 7B Think vs WeVisOne-VL-4B
- Ornith-1.5-122B vs Qwen3.5-4B
- Ornith-1.5-122B vs WeVisOne-VL-4B
- Ornith-1.5-35B-A3B vs Qwen3.5-4B
- Ornith-1.5-35B-A3B vs WeVisOne-VL-4B
- Ornith-1.5-397B vs Qwen3.5-4B
- Ornith-1.5-397B vs WeVisOne-VL-4B
- Ornith-1.5-9B vs Qwen3.5-4B
- Ornith-1.5-9B vs WeVisOne-VL-4B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-4B
- OTel-2.0-LLM-31B-IT vs WeVisOne-VL-4B
- Qwen-AgentWorld-35B-A3B vs Qwen3.5-4B
- Qwen-AgentWorld-35B-A3B vs WeVisOne-VL-4B
- Qwen3-30B-A3B-Instruct-2507 vs Qwen3.5-4B
- Qwen3-30B-A3B-Instruct-2507 vs WeVisOne-VL-4B
- Qwen3-4B-Instruct-2507 vs Qwen3.5-4B
- Qwen3-4B-Instruct-2507 vs WeVisOne-VL-4B
- Qwen3.5-0.8B vs Qwen3.5-4B
- Qwen3.5-0.8B vs WeVisOne-VL-4B
- Qwen3.5-122B-A10B vs Qwen3.5-4B
- Qwen3.5-122B-A10B vs WeVisOne-VL-4B
- Qwen3.5-2B vs Qwen3.5-4B
- Qwen3.5-2B vs WeVisOne-VL-4B
- Qwen3.5-397B-A17B vs Qwen3.5-4B
- Qwen3.5-397B-A17B vs WeVisOne-VL-4B
- Qwen3.5-4B vs Qwen3.5-9B
- Qwen3.5-4B vs Qwen3.6-27B
- Qwen3.5-4B vs Qwen3.6-35B-A3B
- Qwen3.5-4B vs Qwen3.8-27B
- Qwen3.5-4B vs Qwen3.8-Flash-Next
- Qwen3.5-4B vs Qwen3-Coder-30B-A3B-Instruct
- Qwen3.5-4B vs Qwen3-Coder-Next
- Qwen3.5-4B vs Qwen3-Omni-30B-A3B-Instruct
- Qwen3.5-4B vs Qwen3-VL-2B-Instruct
- Qwen3.5-4B vs Qwen3-VL-30B-A3B-Instruct
- Qwen3.5-4B vs Qwen3-VL-32B-Instruct
- Qwen3.5-4B vs Qwen3-VL-4B-Instruct
- Qwen3.5-4B vs Qwen3-VL-8B-Instruct
- Qwen3.5-4B vs Qwopus3.8-27B-Flash-V2
- Qwen3.5-4B vs Recursive Flint
- Qwen3.5-4B vs Ripple-65B Preview
- Qwen3.5-4B vs SenseNova-Loop-9B-Preview
- Qwen3.5-4B vs SmolLM3-3B
- Qwen3.5-4B vs Spark-X2.6-4B
- Qwen3.5-4B vs Step 3.7 Flash
- Qwen3.5-4B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-4B vs Swift 1.5 Qwen3.8-Flash-Next
- Qwen3.5-4B vs ThinkingCap (Qwen3.8 27B)
- Qwen3.5-4B vs Baidu Unlimited-OCR-2
- Qwen3.5-4B vs WeVisOne-VL-2B
- Qwen3.5-4B vs ZAYA1-8B
- Qwen3.5-9B vs WeVisOne-VL-4B
- Qwen3.6-27B vs WeVisOne-VL-4B
- Qwen3.6-35B-A3B vs WeVisOne-VL-4B
- Qwen3.8-27B vs WeVisOne-VL-4B
- Qwen3.8-Flash-Next vs WeVisOne-VL-4B
- Qwen3-Coder-30B-A3B-Instruct vs WeVisOne-VL-4B
- Qwen3-Coder-Next vs WeVisOne-VL-4B
- Qwen3-Omni-30B-A3B-Instruct vs WeVisOne-VL-4B
- Qwen3-VL-2B-Instruct vs WeVisOne-VL-4B
- Qwen3-VL-30B-A3B-Instruct vs WeVisOne-VL-4B
- Qwen3-VL-32B-Instruct vs WeVisOne-VL-4B
- Qwen3-VL-4B-Instruct vs WeVisOne-VL-4B
- Qwen3-VL-8B-Instruct vs WeVisOne-VL-4B
- Qwopus3.8-27B-Flash-V2 vs WeVisOne-VL-4B
- Recursive Flint vs WeVisOne-VL-4B
- Ripple-65B Preview vs WeVisOne-VL-4B
- SenseNova-Loop-9B-Preview vs WeVisOne-VL-4B
- SmolLM3-3B vs WeVisOne-VL-4B
- Spark-X2.6-4B vs WeVisOne-VL-4B
- Step 3.7 Flash vs WeVisOne-VL-4B
- Swift 1.5 Qwen3.8-27B vs WeVisOne-VL-4B
- Swift 1.5 Qwen3.8-Flash-Next vs WeVisOne-VL-4B
- ThinkingCap (Qwen3.8 27B) vs WeVisOne-VL-4B
- WeVisOne-VL-2B vs WeVisOne-VL-4B
- WeVisOne-VL-4B vs ZAYA1-8B
- Baidu Unlimited-OCR-2 vs WeVisOne-VL-4B
Machine-readable
- This page as Markdown
/compare/qwen3-5-4b-vs-wevisone-vl-4b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/qwen3-5-4b.json·/api/v1/tools/wevisone-vl-4b.json - From a terminal
anchor compare qwen3-5-4b wevisone-vl-4b(the CLI) - Over MCP
compare_tools {"a": "qwen3-5-4b", "b": "wevisone-vl-4b"}at/mcp, no key