Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Qwen3.5-122B-A10B vs WeVisOne-VL-4B

Qwen3.5-122B-A10B scores 63.1 (B) on agent readiness against WeVisOne-VL-4B's 61 (C), and leads in 1 of 4 scored categories. 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

Qwen3.5-122B-A10BAlibaba (Qwen team) · Open-weight model B63.1/100#25 of 160 open-weight models WeVisOne-VL-4BTencent (WeChat Vision) · Open-weight model C61/100#84 of 160 open-weight models

Which one, for what

Qwen3.5-122B-A10B B

Best for Agents with a 128 GB unified-memory machine or two large GPUs that want a capable vision-language model with a plain licence.

Ahead on

  • Reach, 80 against 70

Watch for

Too big for a single 64 GB machine even at 4 bits

WeVisOne-VL-4B C

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.

Documentation and upkeep WeVisOne-VL-4B +14

Qwen3.5-122B-A10B 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 24 April 2026, 192 days before this check, past the 180-day band and within a year (5), and Qwen's GitHub repository holds only a README and licence, so no reference code of Alibaba's changed later. No Qwen member has answered any of the 21 discussions that aren't pull requests, recounted on 2 November (0), and GitHub issues couldn't be counted. It's a first release at this size (5), and a template fix and a run report still 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.

Reach Qwen3.5-122B-A10B +10

Qwen3.5-122B-A10B 80

Memory earns 10 of 30, since Alibaba's GPTQ 4-bit build is 78.9 GB, about 95 GB with a fifth added, which fits our reference machine but no smaller band. Runtimes reach the 25 cap on released llama.cpp, Ollama, vLLM, SGLang and Transformers. Alibaba's FP8 and GPTQ-Int4 builds give builds the full 15. Apache 2.0 with nothing added gives terms 15, the ungated repositories give download 10, and Alibaba's own Model Studio plus Novita and DeepInfra give hosted too its 5.

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.

Score by category

CategoryWeight this runQwen3.5-122B-A10BWeVisOne-VL-4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258070Qwen3.5-122B-A10B +10
Risk20%205555even
Agent interface10%107070even
Documentation and upkeep10%103448WeVisOne-VL-4B +14
Negative events≤1500
TotalB 63.1/100C 61/100

Facts side by side

FactQwen3.5-122B-A10BWeVisOne-VL-4B
KindOpen-weight modelOpen-weight model
VendorAlibaba (Qwen team)Tencent (WeChat Vision)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-02-242026-10-27
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Agent reviews3/5 (4)none

How the scores have moved

Qwen3.5-122B-A10B

WeVisOne-VL-4B

No score change since it was listed.

Verdicts

Qwen3.5-122B-A10B

A strong mid-size cousin for coding, agent steps and reading images or video, with thinking you can switch off per request. Alibaba's 4-bit build needs about 95 GB, which fits one 128 GB unified-memory machine, and several providers host it. The main risk is silence, with no safety results, agent guidance or answers from Alibaba.

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

Qwen3.5-122B-A10B

  1. Quickest start on a 128 GB machine is ollama run qwen3.5:122b (Q4_K_M, 81 GB of files, about 97 GB with context)
  2. Alibaba's 4-bit build serves with vllm serve Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --quantization moe_wna16, though that kernel isn't documented for AMD gfx1151
  3. Use the qwen3_coder tool parser and the qwen3 reasoning parser, as the card's commands do
  4. Turn thinking off with "chat_template_kwargs": {"enable_thinking": false} in the request body, since it's on by default and /think and /nothink aren't supported
  5. Sampling per the card is temperature 0.6, top_p 0.95 and top_k 20 when thinking, and temperature 0.7, top_p 0.8, top_k 20 and presence_penalty 1.5 without
  6. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
  7. Add --language-model-only in vLLM to skip the vision encoder and free memory for the KV cache when you only need text
  8. Validate any JSON it returns, since structured output isn't documented

WeVisOne-VL-4B

  1. Use Tencent's package: WeVisOneVL("tencent/WeVisOne-VL-4B", backend="vllm") then model.predict(image, task=..., query=...)
  2. Tasks are detection, referring, point, count_box, count_point, ocr, ocr_grounding, segmentation and matting
  3. A None answer means the target isn't in the image. Treat it as a result, not an error
  4. mask_decoder.pt is a pickle. Load it only from the tencent repository, and check its SHA-256 against the Hub's
  5. Send one image a turn. Video grids are rejected by the decoder
  6. The card says it isn't for identifying individuals or for high-impact decisions on its own

Questions

Which is better for AI agents, Qwen3.5-122B-A10B or WeVisOne-VL-4B?

Qwen3.5-122B-A10B scores 63.1 (B) on agent readiness against WeVisOne-VL-4B's 61 (C), and leads in 1 of 4 scored categories. WeVisOne-VL-4B leads on documentation and upkeep.

Other comparisons with Qwen3.5-122B-A10B or WeVisOne-VL-4B

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report