Sign in

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

Apodex-1.1-mini vs Arete-27B

Apodex-1.1-mini scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 3 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

Apodex-1.1-miniApodex AI · Open-weight model C61/100#41 of 135 open-weight models Arete-27BNous Research · Open-weight model C55.1/100#105 of 135 open-weight models

Which one, for what

Apodex-1.1-mini C

Best for Long-running agent tasks with tools on a 32 GB GPU or Mac, or through Apodex's API, under a plain licence

Ahead on

  • Reach, 85 against 50
  • Risk, 65 against 55
  • Agent interface, 85 against 60

Watch for

No safety results, and agent guidance only from the harness

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 38

Watch for

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

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 Apodex-1.1-mini +35

Apodex-1.1-mini 85

Memory 20, Apodex's Q4_K_M GGUF with its vision projector is 22.6 GB and needs about 27.1 GB with the fifth added, so 32 GB, as do its NVFP4 and GPTQ-Int4 builds. Runtimes 20, the Qwen3.5 MoE architecture runs in released vLLM, SGLang, Transformers and llama.cpp, while Ollama's and LM Studio's entries are the base's, not this model's. Builds 15, Apodex publishes FP8, NVFP4, GPTQ-Int4 and GGUF. Terms 15, Apache 2.0 with nothing added. Download 10, nothing is gated. Hosted 5, Apodex's own API serves it.

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.

Agent interface Apodex-1.1-mini +25

Apodex-1.1-mini 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card says how tools go in and come back and names the parser for SGLang and vLLM, with a full example. Trained tool calling 20, trained for native function calling with parallel calls. Structured output 0. Reasoning control 10, the template turns thinking off per request and the card says the reasoning comes back in reasoning_content. Context 10, 262,144 tokens.

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.

Documentation and upkeep Arete-27B +25

Apodex-1.1-mini 38

Model card 8, it covers intended use, context and languages but not the architecture, parameters, limitations or a knowledge cut-off. Training data 5, a general description with no cut-off. Last change 15, the GGUF build went up on 10 September 2026, 54 days before 3 November. Responsiveness 0, Apodex answered none of the four discussions, unchanged on 3 November 2026. Version policy 5, 1.0-mini stays in its own repository without a note. File health 5, the files agree, but the card's agent example is broken and reports wait without a reply.

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.

Risk Apodex-1.1-mini +10

Apodex-1.1-mini 65

File safety 25, safetensors and GGUF only and nothing from the repositories runs. Provenance 15, the files are in the apodex organisation its site links to, with a SHA-256 for every weight file and a SHA256SUMS file for the GGUF. Safety evaluation 0, none published. Agent guidance 5, the recommended harness documents approval gates and a sandbox boundary, but nothing on prompt injection or refusals for the model. Licence risk 15, Apache 2.0 from Qwen3.5-35B-A3B through to this model with no conditions added. Security programme 5, the harness has a disclosure policy with a private address, with no route shown for the weights.

Arete-27B 55

File safety 25, safetensors only and no remote code. Provenance 15, Nous Research's own organisation, linked from its blog, with a hash on every file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 15, plain Apache 2.0. Security programme 0, no way to report a flaw found. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Score by category

CategoryWeight this runApodex-1.1-miniArete-27BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258550Apodex-1.1-mini +35
Risk20%206555Apodex-1.1-mini +10
Agent interface10%108560Apodex-1.1-mini +25
Documentation and upkeep10%103863Arete-27B +25
Negative events≤1500
TotalC 61/100C 55.1/100

Facts side by side

FactApodex-1.1-miniArete-27B
KindOpen-weight modelOpen-weight model
VendorApodex AINous Research
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-08-252026-11-06
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.3/5 (4)none

Verdicts

Apodex-1.1-mini

An agent cousin fine-tuned from Qwen3.5-35B-A3B for long tasks with files, code and tools, with parallel tool calling and about 3B active parameters. It needs 32 GB for Apodex's GGUF, NVFP4 or GPTQ-Int4 builds or about 86 GB in BF16, and Apodex's API serves it too. The main risks are no safety results and no replies from the publisher.

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.

Before you call either

Apodex-1.1-mini

  1. Serve it with vllm serve apodex/Apodex-1.1-mini --enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3, or the same parsers in SGLang, so tool calls and reasoning come back parsed
  2. For llama.cpp, llama-server -hf apodex/Apodex-1.1-mini-GGUF:Q4_K_M --jinja --reasoning-format deepseek, and the card passes the repository's chat_template.jinja with --chat-template-file
  3. Pass tools through the API's tools parameter rather than in the system prompt, as the card asks
  4. The card recommends temperature 1.0, top_p 0.95, repetition_penalty 1.05 and max_tokens up to 32,768
  5. Send your own system prompt, or set identity_mode, since the template otherwise adds an Apodex identity block
  6. The template keeps all earlier reasoning in the context unless preserve_thinking is false, which grows long agent sessions
  7. Thinking is on by default, send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  8. The card's Python example has a broken line where it runs the tool (available_toolsname), so fix it to available_tools[name](**args) before running
  9. Validate JSON output yourself, since structured output isn't documented

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

Questions

Which is better for AI agents, Apodex-1.1-mini or Arete-27B?

Apodex-1.1-mini scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 3 of 4 scored categories. Arete-27B leads on documentation and upkeep.

Other comparisons with Apodex-1.1-mini or Arete-27B

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