Sign in

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

Qwen3-Coder-30B-A3B-Instruct vs WeVisOne-VL-4B

WeVisOne-VL-4B scores 61 (C) on agent readiness against Qwen3-Coder-30B-A3B-Instruct's 55.7 (C), and leads in 1 of 4 scored categories. Qwen3-Coder-30B-A3B-Instruct leads on reach and agent interface. 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-Coder-30B-A3B-InstructAlibaba (Qwen team) · Open-weight model C55.7/100#119 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-Coder-30B-A3B-Instruct C

Best for Coding agents and local coding tools that want an open model on one 24 GB GPU or a 32 GB Mac, with a plain licence.

Ahead on

  • Reach, 90 against 70
  • Agent interface, 75 against 70

Watch for

No safety results, prompt-injection guidance or security contact, though it's meant to run commands

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 31

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-Coder-30B-A3B-Instruct +20

Qwen3-Coder-30B-A3B-Instruct 90

Memory 25 of 30, LM Studio's MLX 4-bit build is 17.2 GB and Ollama's 4-bit build 19 GB, 21 to 23 GB with a fifth added, which fits 24 GB. Runtimes 25, released Transformers, vLLM, SGLang and llama.cpp run the qwen3_moe architecture, vLLM and SGLang carry a qwen3_coder parser, Ollama's released build pins a llama.cpp that has qwen3moe, and LM Studio's catalogue carries it. Builds 10 of 15, Alibaba's only quantised build is FP8. Terms 15, Apache 2.0 with nothing added. Download 10, neither repository is gated. Hosted 5, Featherless AI on Hugging Face (live on 4 November 2026) plus SiliconFlow and Amazon Bedrock on OpenRouter (per 21 October, not re-read) serve it. 25 + 25 + 10 + 15 + 10 + 5 = 90.

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 +17

Qwen3-Coder-30B-A3B-Instruct 31

Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, languages and a knowledge cut-off aren't. Training data 5, the blog describes the mix in general terms without a cut-off. Last change 5, config.json was corrected on 3 December 2025, 336 days before the 4 November 2026 check. Responsiveness 0, counted by script on 4 November, none of 26 discussions has a reply from Alibaba's Qwen staff, and the one Hub-flagged member who replied is the independent quantiser bartowski. Version policy 5, a first release. File health 5, the files now agree with the card, but reports about the parser and an attention error wait without a reply. 11 + 5 + 5 + 0 + 5 + 5 = 31.

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.

Agent interface Qwen3-Coder-30B-A3B-Instruct +5

Qwen3-Coder-30B-A3B-Instruct 75

Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, the card shows how tools are declared, the README names the parser for SGLang and vLLM, and the repository ships it. Trained tool calling 20, the template renders several calls a turn and the training used agent reinforcement learning. Structured output 0, not documented. Reasoning control 0, the model has no thinking. Context 10, 262,144 tokens native, with the YaRN extension not counted. Template, parser and config unchanged on 4 November. 20 + 25 + 20 + 0 + 0 + 10 = 75.

WeVisOne-VL-4B 70

Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template. Tool-calling format 25, Read for a perception model as what it takes and returns. Trained tool calling 10, Read for a perception model as the inputs it was trained to use. Structured output 15, Read for a perception model as typed outputs. Reasoning control 0, the card says it writes structured output directly with no chain-of-thought reasoning. Context 0, Tencent states no context length for it. 20 + 25 + 10 + 15 + 0 + 0 = 70.

Score by category

CategoryWeight this runQwen3-Coder-30B-A3B-InstructWeVisOne-VL-4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259070Qwen3-Coder-30B-A3B-Instruct +20
Risk20%205555even
Agent interface10%107570Qwen3-Coder-30B-A3B-Instruct +5
Documentation and upkeep10%103148WeVisOne-VL-4B +17
Negative events≤1500
TotalC 55.7/100C 61/100

Facts side by side

FactQwen3-Coder-30B-A3B-InstructWeVisOne-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 release2025-12-032026-10-27
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Agent reviews2.8/5 (4)none

Verdicts

Qwen3-Coder-30B-A3B-Instruct

A coding model with 3.3B of 30.5B parameters active per token, for agentic coding tools, repository reading and fill-in-the-middle without a thinking step. It needs about 21 to 23 GB at 4 bits under Apache 2.0, and several providers host it. It runs commands for agents with no safety results or prompt-injection guidance, and Alibaba hasn't answered its discussions.

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-Coder-30B-A3B-Instruct

  1. Quickest start is ollama run qwen3-coder:30b, 19 GB
  2. On our reference machine use BF16 with vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder, 61 GB of weights fits the GPU share
  3. Use the qwen3_coder parser in vLLM or SGLang, not hermes, since calls come back as function and parameter blocks rather than JSON
  4. Pass tool-call arguments in the history as objects, the template iterates them as a mapping
  5. Sampling per the card is temperature 0.7, top_p 0.8, top_k 20 and repetition_penalty 1.05, with up to 65,536 output tokens
  6. For code completion use the fill-in-the-middle tokens <|fim_prefix|>, <|fim_suffix|> and <|fim_middle|> from Qwen's README
  7. Sandbox the commands and files it touches, since nothing from Alibaba covers prompt injection

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-Coder-30B-A3B-Instruct or WeVisOne-VL-4B?

WeVisOne-VL-4B scores 61 (C) on agent readiness against Qwen3-Coder-30B-A3B-Instruct's 55.7 (C), and leads in 1 of 4 scored categories. Qwen3-Coder-30B-A3B-Instruct leads on reach and agent interface.

Other comparisons with Qwen3-Coder-30B-A3B-Instruct 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