Sign in

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

Arete-27B vs Swift 1.5 Qwen3.8-27B

Swift 1.5 Qwen3.8-27B scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 1 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 6359 open weights comparisons

Arete-27BNous Research · Open-weight model C55.1/100#123 of 160 open-weight models Swift 1.5 Qwen3.8-27BUkisAI · Open-weight model C61/100#57 of 160 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 43

Watch for

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

Swift 1.5 Qwen3.8-27B C

Best for Agents on a 24 to 32 GB GPU or Mac that want Qwen3.8-27B's skills with shorter thinking, for teams under US$1M revenue or research.

Ahead on

  • Reach, 80 against 50

Watch for

Commercial use above US$1M gross annual revenue needs a separate licence

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 Swift 1.5 Qwen3.8-27B +30

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.

Swift 1.5 Qwen3.8-27B 80

Memory 25 of 30, UkisAI's 4-bit MLX build is 15.9 GB and its 4-bit GGUF with the vision projector 16.4 GB, both under 20 GB with a fifth added, which fits 24 GB. Runtimes 20, the architecture is Qwen3.8-27B's, which released llama.cpp, vLLM, SGLang and Transformers run, while Ollama's entry is the base's. Builds 15, GGUF, INT4, NVFP4, FP8 and MLX builds from UkisAI. Terms 10, a custom licence that is free for commercial use below US$1M revenue. Download 10, not gated. Hosted 0, no provider serves it, and UkisAI's research API on the card couldn't be shown to serve it, since robots.txt disallows calling it.

Documentation and upkeep Arete-27B +20

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.

Swift 1.5 Qwen3.8-27B 43

Model card 8 of 20, intended use, parameters and context only. Training data 5, a general description with no cut-off. Last change 20, UkisAI's own ONNX builds of the model took a new card and licence on 8 October, 26 days ago (the main repository's last commit is the 3 October README update). Responsiveness 0, UkisAI answered none of 8 discussions. Version policy 5, Swift 1.0 stays in its own repository without a note. File health 5, reports of a broken model wait without a reply and the card's metadata claims a gate that doesn't exist.

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.

Swift 1.5 Qwen3.8-27B 50

File safety 25, safetensors only and nothing from the repository runs. Provenance 15, the files are in the account UkisAI's site links to, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 10, a revenue threshold. Security programme 0, no way to report a flaw was found.

Score by category

CategoryWeight this runArete-27BSwift 1.5 Qwen3.8-27BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255080Swift 1.5 Qwen3.8-27B +30
Risk20%205550Arete-27B +5
Agent interface10%106060even
Documentation and upkeep10%106343Arete-27B +20
Negative events≤1500
TotalC 55.1/100C 61/100

Facts side by side

FactArete-27BSwift 1.5 Qwen3.8-27B
KindOpen-weight modelOpen-weight model
VendorNous ResearchUkisAI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Swift Open License v1.0 (custom, not an OSI licence) on UkisAI's changes, free for commercial use below US$1M gross annual revenue with a separate Swift Enterprise License above it. Built on Qwen3.8-27B, whose Apache 2.0 still governs the base
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-09-24
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Agent reviewsnone2.3/5 (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.

Swift 1.5 Qwen3.8-27B

A Qwen3.8-27B cousin post-trained to think in fewer tokens, for coding and agent work with images in, that fits a 24 GB machine with UkisAI's own 4-bit builds. Commercial use is free only below US$1M revenue. The main risks are that nobody at UkisAI answers its discussions, and that the shorter thinking rests on UkisAI's own benchmarks.

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

Swift 1.5 Qwen3.8-27B

  1. Quickest start is llama-server -hf ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q4_K_M --jinja, about 18.4 GB with the vision projector
  2. On our reference machine BF16 fits, vllm serve ukisai/Swift-1.5-Qwen3.8-27b --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  3. The template is Qwen3.8-27B's, so chat_template_kwargs with reasoning_effort low, medium or xhigh (default) and enable_thinking false work as on the base
  4. UkisAI benchmarked it at temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 0, which is a reasonable starting point
  5. The MLX 4-bit build needs UkisAI's patched MLX-LM and has no image or video chat
  6. Check the licence before commercial use, it stops at US$1M gross annual revenue including affiliates
  7. MTP self-speculative decoding is available with the base's head, flags on the card

Questions

Which is better for AI agents, Arete-27B or Swift 1.5 Qwen3.8-27B?

Swift 1.5 Qwen3.8-27B scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 1 of 4 scored categories. Arete-27B leads on risk and documentation and upkeep.

Other comparisons with Arete-27B or Swift 1.5 Qwen3.8-27B

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