Sign in

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

Arete-27B vs Ornith-1.5-35B-A3B

Ornith-1.5-35B-A3B scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 2 of 4 scored categories. Arete-27B leads on risk and 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 Ornith-1.5-35B-A3BOrnith · Open-weight model C61/100#50 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

  • Risk, 55 against 50
  • Documentation and upkeep, 63 against 36

Watch for

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

Ornith-1.5-35B-A3B C

Best for Local coding and terminal agents on a 24 to 32 GB GPU or a Mac, where a clear licence file and an answering publisher aren't required

Ahead on

  • Reach, 90 against 50
  • Agent interface, 85 against 60

Watch for

No LICENSE file though the card links one, and no notice for the Apache 2.0 Qwen3.5 and Gemma 4 work it builds on

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 Ornith-1.5-35B-A3B +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.

Ornith-1.5-35B-A3B 90

Memory 25, since Ornith's own MLX 4-bit build is 19.5 GB and needs about 23.4 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGUF, NVFP4 build and Ollama's build each need 32 GB. Runtimes 25, the most the line gives, from vLLM 0.19.1 (still in v0.33.0), SGLang 0.5.9, Transformers 5.8.1, llama.cpp's qwen35moe architecture, Ollama's library and LM Studio's catalogue for the qwen35moe architecture. Builds 15, Ornith publishes FP8, NVFP4, GGUF and MLX at several precisions. Terms 15, MIT as named in the card's metadata on 21 October 2026, with nothing added, read by its terms though the repository has no licence file. Download 10, nothing is gated. Hosted 0, Ornith runs no API and no inference provider serves it. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Documentation and upkeep Arete-27B +27

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.

Ornith-1.5-35B-A3B 36

Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data 5, a description of the method with no data or cut-off. Last change 20, Ornith deleted configuration.json and a marker file from its FP8 build on 20 October 2026, 14 days ago, which this run counts as a change to the files. Responsiveness 0, Ornith answered none of the 36 questions and reports. Version policy 0, a weight shard, every GGUF file, an FP8 shard and the NVFP4 shards were replaced in place between 23 and 26 August with no note. File health 0, the card links a missing LICENSE, and the two chat templates differ. 11 + 5 + 20 + 0 + 0 + 0 = 36.

Agent interface Ornith-1.5-35B-A3B +25

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.

Ornith-1.5-35B-A3B 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card shows how tools go in and how calls come back and names the parser for vLLM and SGLang. Trained tool calling 20, Ornith trains it on agent tasks and the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, Ornith's template turns thinking off per request with enable_thinking set to false and the card says the reasoning comes back in reasoning_content, though the card doesn't name the switch. Context 10, 262,144 tokens native.

Risk Arete-27B +5

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.

Ornith-1.5-35B-A3B 50

File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from the repository. Provenance 15, the files come from the ornith-ai organisation Ornith's blog links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 10, MIT carries no policy, threshold or changeable terms, but the card's licence link is broken. Security programme 0, no security.txt, disclosure policy or security contact.

Score by category

CategoryWeight this runArete-27BOrnith-1.5-35B-A3BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255090Ornith-1.5-35B-A3B +40
Risk20%205550Arete-27B +5
Agent interface10%106085Ornith-1.5-35B-A3B +25
Documentation and upkeep10%106336Arete-27B +27
Negative events≤1500
TotalC 55.1/100C 61/100

Facts side by side

FactArete-27BOrnith-1.5-35B-A3B
KindOpen-weight modelOpen-weight model
VendorNous ResearchOrnith
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-08-23
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.3/5 (4)

How the scores have moved

Arete-27B

No score change since it was listed.

Ornith-1.5-35B-A3B

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.

Ornith-1.5-35B-A3B

A mid-size coding and terminal-agent cousin with about 3B active parameters, XML tool calls that vLLM and SGLang parse and 262,144 tokens of context. It runs in about 24 GB from Ornith's MLX 4-bit build or 32 GB from its GGUF. The main risk is an absent publisher, with no licence file, safety results or replies to 36 reports.

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

Ornith-1.5-35B-A3B

  1. Start it with ollama run ornith-1.5:35b, or llama-server -hf ornith-ai/Ornith-1.5-35B-A3B-GGUF --port 8000 -c 262144 as the card gives it
  2. In vLLM pass --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3, and in SGLang --tool-call-parser qwen3_coder --reasoning-parser qwen3, so tool calls and reasoning come back parsed
  3. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  4. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
  5. Use temperature 0.6, top_p 0.95, top_k 20 for general tasks and temperature 1.0 to reproduce the card's benchmarks
  6. Pin a revision when you download, since Ornith has replaced files in place, and add mmproj-Ornith-1.5-35B-BF16.gguf (0.9 GB) for image input in llama.cpp
  7. Validate JSON output yourself, since structured output isn't documented

Questions

Which is better for AI agents, Arete-27B or Ornith-1.5-35B-A3B?

Ornith-1.5-35B-A3B scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 2 of 4 scored categories. Arete-27B leads on risk and documentation and upkeep.

Other comparisons with Arete-27B or Ornith-1.5-35B-A3B

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