Sign in

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

Qwen-AgentWorld-35B-A3B vs Qwen3-VL-8B-Instruct

Qwen3-VL-8B-Instruct scores 54.9 (C) on agent readiness against Qwen-AgentWorld-35B-A3B's 52.1 (D), and leads in 2 of 4 scored categories. Qwen-AgentWorld-35B-A3B 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

Qwen-AgentWorld-35B-A3BAlibaba (Qwen team) · Open-weight model D52.1/100#141 of 160 open-weight models Qwen3-VL-8B-InstructAlibaba (Qwen team) · Open-weight model C54.9/100#124 of 160 open-weight models

Which one, for what

Qwen-AgentWorld-35B-A3B D

Best for Agent builders who want to train or test an agent against simulated tools, terminals, browsers and phones on a 128 GB machine

Ahead on

  • Documentation and upkeep, 41 against 31

Watch for

Not a general assistant, and the card doesn't describe using it to call tools

Qwen3-VL-8B-Instruct C

Best for An agent with 8 GB or more to spare that needs a local model to read images, documents and video

Ahead on

  • Reach, 100 against 55
  • Agent interface, 60 against 50

Watch for

No safety evaluation, agent-use guidance or security contact

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-VL-8B-Instruct +45

Qwen-AgentWorld-35B-A3B 55

Memory 10, Alibaba's only build is the BF16 safetensors, 69.32 GB, and 69.32 GB × 1.2 = 83.2 GB, above 64 GB and inside the reference machine's GPU share. Runtimes 20, Four released runtimes run the architecture, vLLM 0.33.0 (Qwen3_5MoeForConditionalGeneration), SGLang 0.5.23, Transformers 5.22.2 (qwen3_5_moe) and llama.cpp b12242 (its Qwen conversion code). Builds 0, Alibaba publishes the BF16 weights only. Terms 15, Apache 2.0, an OSI licence, in the metadata and as a LICENSE file, with no use policy or other terms added. Download 10, the repository isn't gated, so the files download with no account and no terms to accept. Hosted 0, Hugging Face lists no inference provider for the model (an empty provider mapping on 10 November 2026). 10 + 20 + 0 + 15 + 10 + 0 = 55.

Qwen3-VL-8B-Instruct 100

Alibaba's own Q4_K_M GGUF is 5.03 GB, so with a fifth added it needs about 6 GB and fits in 16 GB (30). Transformers 4.57.0, vLLM, SGLang and llama.cpp run it in released versions, and Ollama v0.40.14 pins llama.cpp b11963, which has the qwen3vl architecture, so Ollama is credited through its pin; five runtimes reach the 25 cap. Alibaba publishes FP8 and GGUF builds at F16, Q8_0 and Q4_K_M (15). Apache 2.0 with nothing added (15). No gate and no account (10). Featherless is live in the Hub's provider mapping on 4 November, and Parasail served it per the 21 October check, not re-read, so it's hosted too (5). Novita's mapping still shows an error and isn't counted. 30+25+15+15+10+5 = 100.

Agent interface Qwen3-VL-8B-Instruct +10

Qwen-AgentWorld-35B-A3B 50

Chat template 20, chat_template.jinja in the repository, the same as the template in tokenizer_config.json. Tool-calling format 10, only the template says how tools are declared and how calls come back. Trained tool calling 10, the template renders several tool_call blocks in one turn, but the card presents the model as a simulator of what tools and environments return, not as a tool caller. Structured output 0, no JSON or JSON Schema output documented for the model. Reasoning control 0, the card says thinking is on by default and names the qwen3 reasoning parser, but doesn't say how to turn thinking off or budget it. Context 10, 262,144 tokens native per the card and the text config. 20 + 10 + 10 + 0 + 0 + 10 = 50.

Qwen3-VL-8B-Instruct 60

A Jinja chat template in the repository (20). The tool-call format lives only in the template, Hermes-style JSON in tool_call tags, and Alibaba names no parser (10). Trained for function calling with several calls allowed in a turn (20). No documented structured output (0). No thinking mode in this edition, so reasoning control scores 0 by the rule. 262,144 tokens of native context (10). 20+10+20+0+0+10 = 60.

Documentation and upkeep Qwen-AgentWorld-35B-A3B +10

Qwen-AgentWorld-35B-A3B 41

Model card 11, the card gives intended use (simulating agent environments), architecture, parameters and context length. Training data 5, A general description without a cut-off, the three training stages and a statement that no outputs from external API services were included. Last change 10, the last commit was on 25 June 2026, an update to the card, 138 days before this check, past 90 days and within 180. Responsiveness 0, 10 discussions that aren't pull requests, opened between 24 June and 5 July 2026. Version policy 5, A first release, with nothing replaced. File health 10, Config, both copies of the template and the card agree on the architecture and the context. 11 + 5 + 10 + 0 + 5 + 10 = 41.

Qwen3-VL-8B-Instruct 31

The card misses limitations, languages and a cut-off (11). Training data is described only in the technical report, with no cut-off (5). The last change to code that runs it was the qwen-vl-utils fix merged on 4 January 2026, and the weights haven't changed since November 2025; the Hub commits for all three repositories and the QwenLM/Qwen3-VL head (30 January 2026) were the same on 4 November (5). Of 34 Hugging Face discussions on 4 November, the 19 that aren't pull requests (newest 23 August 2026) have no reply from Qwen, and GitHub issues weren't counted (0). Earlier versions kept in their own repositories without notes (5). Two reports wait without a reply (5). 11+5+5+0+5+5 = 31.

Score by category

CategoryWeight this runQwen-AgentWorld-35B-A3BQwen3-VL-8B-InstructEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%2555100Qwen3-VL-8B-Instruct +45
Risk20%205555even
Agent interface10%105060Qwen3-VL-8B-Instruct +10
Documentation and upkeep10%104131Qwen-AgentWorld-35B-A3B +10
Negative events≤1500
TotalD 52.1/100C 54.9/100

Facts side by side

FactQwen-AgentWorld-35B-A3BQwen3-VL-8B-Instruct
KindOpen-weight modelOpen-weight model
VendorAlibaba (Qwen team)Alibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-06-252025-11-01
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (4)

Verdicts

Qwen-AgentWorld-35B-A3B

A specialist, not a chat model. It plays the environment an agent acts in, across seven domains, so you can train or test an agent without the real thing. Alibaba ships BF16 only, which fits a 128 GB machine, and hasn't answered a discussion on it or changed the files since June.

Qwen3-VL-8B-Instruct

Qwen3-VL-8B-Instruct reads screenshots, documents, charts and video, and Alibaba's Q4_K_M GGUF needs about 6 GB. Transformers, vLLM, SGLang, llama.cpp and Ollama run it under plain Apache 2.0. It has no thinking mode, documents tool calls only in the template, and has no published safety work, so add guardrails before it drives a GUI.

Before you call either

Qwen-AgentWorld-35B-A3B

  1. Use it as the environment, not the agent. Give it the domain's system prompt from Alibaba's GitHub repository, the history and the agent's action, and it returns the predicted observation
  2. With vLLM pass --language-model-only, or startup fails on the missing vision weights
  3. Use temperature 0.6, top_p 0.95 and top_k 20, and allow up to 32,768 output tokens, as the card recommends
  4. Keep at least 128K of context, since the simulation depends on the history
  5. Thinking is on by default and comes back through the qwen3 reasoning parser
  6. A simulated observation is a prediction. Check anything that matters against the real environment

Qwen3-VL-8B-Instruct

  1. Start it with llama-server -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_M --jinja -c 32768, or ollama run qwen3-vl:8b-instruct
  2. In Ollama the plain qwen3-vl:8b tag is the Thinking edition, so name 8b-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

Questions

Which is better for AI agents, Qwen-AgentWorld-35B-A3B or Qwen3-VL-8B-Instruct?

Qwen3-VL-8B-Instruct scores 54.9 (C) on agent readiness against Qwen-AgentWorld-35B-A3B's 52.1 (D), and leads in 2 of 4 scored categories. Qwen-AgentWorld-35B-A3B leads on documentation and upkeep.

Other comparisons with Qwen-AgentWorld-35B-A3B or Qwen3-VL-8B-Instruct

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