Sign in

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

Arete-27B vs Qwen3-30B-A3B-Instruct-2507

Qwen3-30B-A3B-Instruct-2507 scores 56.6 (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 Qwen3-30B-A3B-Instruct-2507Alibaba (Qwen team) · Open-weight model C56.6/100#96 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 26

Watch for

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

Qwen3-30B-A3B-Instruct-2507 C

Best for Agents that want an instruct model with tool calling on one 24 GB GPU or a 32 GB Mac, with a plain licence and a 262,144-token context.

Ahead on

  • Reach, 90 against 50
  • Agent interface, 75 against 60

Watch for

No safety results, prompt-injection 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 Qwen3-30B-A3B-Instruct-2507 +40

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.

Qwen3-30B-A3B-Instruct-2507 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, and Ollama's library and LM Studio's catalogue carry 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 plus DekaLLM and SiliconFlow on OpenRouter serve it. On 4 November both repositories were still ungated with no file changed since 17 September 2025, and Featherless AI was still live in the Hub's provider mapping (OpenRouter's providers per 21 October). 25 + 25 + 10 + 15 + 10 + 5 = 90.

Documentation and upkeep Arete-27B +37

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.

Qwen3-30B-A3B-Instruct-2507 26

Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, named languages and a knowledge cut-off aren't. Training data 5, the cited Qwen3 report describes the data in general terms without a cut-off. Last change 0, the files and card last changed on 17 September 2025 (Hub lastModified on 4 November), and QwenLM/Qwen3's commits since are documentation only (the newest 8 January 2026). Responsiveness 0, counted by script on 4 November, with 32 discussions, 23 not pull requests (the newest 18 June 2026), and the only reply from a Qwen organisation member is Haihao's on discussion 3 (30 July 2025), who isn't counted as the publisher's staff (the ehartford and danielhanchen reading). Version policy 5, the older Qwen3-30B-A3B stays in its own repository without a note. File health 5, the files agree with the card but reports about the 1M mode wait without a reply. 11 + 5 + 0 + 0 + 5 + 5 = 26.

Agent interface Qwen3-30B-A3B-Instruct-2507 +15

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.

Qwen3-30B-A3B-Instruct-2507 75

Chat template 20, a Jinja template in tokenizer_config.json. Tool-calling format 25, Qwen's own Function Calling guide documents the Hermes-style declaration and how calls come back, and names vLLM's hermes parser. Trained tool calling 20, the template allows one or more calls a turn. Structured output 0, not documented for the model, and Qwen's docs only point to vLLM's generic guided decoding. Reasoning control 0, this edition has no thinking. Context 10, 262,144 tokens native, with the 1M mode not counted. Template and config unchanged on 4 November. 20 + 25 + 20 + 0 + 0 + 10 = 75.

Score by category

CategoryWeight this runArete-27BQwen3-30B-A3B-Instruct-2507Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255090Qwen3-30B-A3B-Instruct-2507 +40
Risk20%205555even
Agent interface10%106075Qwen3-30B-A3B-Instruct-2507 +15
Documentation and upkeep10%106326Arete-27B +37
Negative events≤1500
TotalC 55.1/100C 56.6/100

Facts side by side

FactArete-27BQwen3-30B-A3B-Instruct-2507
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 release2026-11-062025-09-17
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (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.

Qwen3-30B-A3B-Instruct-2507

A general-purpose instruct model with 3.3B of 30.5B parameters active per token, for instruction following, tool calling and long documents without a thinking step. It needs about 21 to 23 GB at 4 bits under Apache 2.0, and providers host it. Its files haven't changed in over a year, Alibaba hasn't answered its discussions, and no safety results are published.

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

Qwen3-30B-A3B-Instruct-2507

  1. Quickest start is ollama run qwen3:30b-instruct, 19 GB. Plain qwen3:30b and qwen3:30b-a3b are the Thinking-2507 edition, not this one
  2. On our reference machine use BF16 with vllm serve Qwen/Qwen3-30B-A3B-Instruct-2507 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser hermes, 61 GB of weights fits the GPU share
  3. Use the hermes parser in vLLM or qwen25 in SGLang, the template emits JSON inside tool_call tags
  4. Don't pass enable_thinking, this edition never thinks and the card says the flag isn't needed
  5. Sampling per the card is temperature 0.7, top_p 0.8, top_k 20 and min_p 0, with presence_penalty up to 2 against repetition
  6. Leave config.json as it is unless you need more than 262,144 tokens, the 1M mode swaps in config_1m.json and runs one sequence at a time
  7. Validate JSON yourself or use the runtime's guided decoding, since structured output isn't documented

Questions

Which is better for AI agents, Arete-27B or Qwen3-30B-A3B-Instruct-2507?

Qwen3-30B-A3B-Instruct-2507 scores 56.6 (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 Qwen3-30B-A3B-Instruct-2507

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