Sign in

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

Arete-27B vs Qwen3.5-4B

Qwen3.5-4B scores 61.2 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 2 of 4 scored categories. Arete-27B 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 4969 open weights comparisons

Arete-27BNous Research · Open-weight model C55.1/100#105 of 135 open-weight models Qwen3.5-4BAlibaba (Qwen team) · Open-weight model C61.2/100#38 of 135 open-weight models

Which one, for what

Arete-27B C

Best for Agents that want Qwen3.8-27B's coding and tool use without its handling of politically sensitive topics, on a 24 GB card or a 128 GB machine

Ahead on

  • Documentation and upkeep, 63 against 34

Watch for

No quantised build from Nous Research, so the GGUF route depends on a third party

Qwen3.5-4B C

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 50
  • Agent interface, 70 against 60

Watch for

No quantised build from Alibaba for this size

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 +35

Arete-27B 50

Memory 10, the only build from Nous Research is the 54.7 GB BF16 release, which needs about 66 GB and fits the reference machine. Runtimes 15, vLLM, SGLang and Transformers run the base's architecture from those files, and llama.cpp isn't credited because Nous Research publishes no GGUF. Builds 0, no quantised build of its own. Terms 15, Apache 2.0. Download 10, not gated. Hosted 0, no provider. 10 + 15 + 0 + 15 + 10 + 0 = 50.

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.

Documentation and upkeep Arete-27B +29

Arete-27B 63

Model card 8, no limitations, context length, languages or cut-off. Training data 20, the training pairs and the evaluation set are published with their counts. Last change 20, a commit on 6 November 2026. Responsiveness 0, none of 13 discussions has a reply from Nous Research. Version policy 5, a first release. File health 10, the files agree. 8 + 20 + 20 + 0 + 5 + 10 = 63.

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.

Agent interface Qwen3.5-4B +10

Arete-27B 60

Chat template 20, a Jinja file in the repository. Tool-calling format 10, only the template says it. Trained tool calling 20, several calls a turn and agentic work as an intended use. Structured output 0 and reasoning control 0, neither is documented on the card. Context 10, 262,144 tokens native. 20 + 10 + 20 + 0 + 0 + 10 = 60.

Qwen3.5-4B 70

The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the declaration and call format to the template. Thinking turns off per request and comes back in think tags split by the qwen3 parser (10), and 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model.

Score by category

CategoryWeight this runArete-27BQwen3.5-4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255085Qwen3.5-4B +35
Risk20%205555even
Agent interface10%106070Qwen3.5-4B +10
Documentation and upkeep10%106334Arete-27B +29
Negative events≤1500
TotalC 55.1/100C 61.2/100

Facts side by side

FactArete-27BQwen3.5-4B
KindOpen-weight modelOpen-weight model
VendorNous ResearchAlibaba (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 release2026-11-062026-03-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

Verdicts

Arete-27B

Qwen3.8-27B with its answers on politically sensitive topics retrained, four days old when read. The training data is published, which is rare. Nous Research ships BF16 only, so a small machine runs it from bartowski's GGUF, and the card documents none of the tool or thinking controls it inherits.

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.

Before you call either

Arete-27B

  1. Start it with llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M --jinja, a third party's conversion, or serve the BF16 files with vLLM
  2. Use the base's parsers in vLLM, --reasoning-parser qwen3 --tool-call-parser qwen3_coder, and check tool calls first, since the template differs slightly from Qwen3.8-27B's
  3. Thinking switches with enable_thinking in the template. The card's own evaluation ran with it off
  4. Expect answers on politically sensitive topics to differ from Qwen3.8-27B's. That is what the fine-tune is for
  5. Validate JSON output yourself, since structured output isn't documented

Qwen3.5-4B

  1. Smallest start is ollama run qwen3.5:4b (Q4_K_M, about 4 GB with context)
  2. 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
  3. 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
  4. 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=1.5 without thinking
  5. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
  6. Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, Arete-27B or Qwen3.5-4B?

Qwen3.5-4B scores 61.2 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 2 of 4 scored categories. Arete-27B leads on documentation and upkeep.

Other comparisons with Arete-27B or Qwen3.5-4B

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