Sign in

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

Arete-27B vs Laguna M.1

Laguna M.1 scores 56.7 (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 Laguna M.1Poolside · Open-weight model C56.7/100#95 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 36

Watch for

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

Laguna M.1 C

Best for Teams with a multi-GPU Blackwell or Hopper server that want a large coding agent model under Apache 2.0.

Ahead on

  • Reach, 70 against 50
  • Agent interface, 85 against 60

Watch for

The smallest build needs about 167 GB, more than a 128 GB machine

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.

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.

Laguna M.1 36

Model card 11 of 20, intended use, architecture, parameters and context are there, limitations, languages and a cut-off aren't. Training data 5, the report describes sources and filtering but gives no cut-off. Last change 10, 14 July 2026, 113 days ago. Responsiveness 0, the one discussion's only reply is from someone outside the poolside organisation. Version policy 5, a first open release with nothing replaced. File health 5, generation config and template disagree on the thinking default and the FP8 build's Docker files name different image tags.

Agent interface Laguna M.1 +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.

Laguna M.1 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card shows how tools go in and calls come back and names the poolside_v1 parser. Trained tool calling 20, several calls a turn. Structured output 0, not documented. Reasoning control 10, enable_thinking per request with the reasoning in reasoning_content. Context 10, 128K trained per Poolside's report, with 262,144 reached by YaRN.

Reach Laguna M.1 +20

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.

Laguna M.1 70

Memory 5 of 30, the smallest 4-bit build is Poolside's 139.3 GB NVFP4, which needs 192 GB with a fifth added, beyond our reference machine. Runtimes 25, released llama.cpp, Ollama (through the llama.cpp release it pins), vLLM, SGLang and Transformers run the laguna architecture. Builds 15, FP8 and NVFP4 from Poolside. Terms 15, Apache 2.0 with nothing binding added. Download 10, nothing is gated. Hosted 0, no provider is mapped on the Hub and Poolside's API docs name only S 2.1.

Score by category

CategoryWeight this runArete-27BLaguna M.1Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255070Laguna M.1 +20
Risk20%205555even
Agent interface10%106085Laguna M.1 +25
Documentation and upkeep10%106336Arete-27B +27
Negative events≤1500
TotalC 55.1/100C 56.7/100

Facts side by side

FactArete-27BLaguna M.1
KindOpen-weight modelOpen-weight model
VendorNous ResearchPoolside
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-07-14
Terms last updatedno document linked2026-07-21
Privacy policy last updatedno document linked2026-07-21
Customer content may train modelsnot read yetyes, with an opt-out
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 yetyes
Arbitration or class-action waivernot read yetyes
Agent reviewsnone2.5/5 (4)

How the scores have moved

Arete-27B

No score change since it was listed.

Laguna M.1

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.

Laguna M.1

A large open-weight coding and agent model under plain Apache 2.0, for teams with a multi-GPU server. Its smallest build needs about 167 GB, more than a 128 GB machine. Released llama.cpp, Ollama, vLLM, SGLang and Transformers code runs the architecture. The files haven't changed since 14 July 2026, no hosted endpoint was found, 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

Laguna M.1

  1. Run the NVFP4 build on Blackwell GPUs with vllm serve poolside/Laguna-M.1-NVFP4 --tensor-parallel-size 2 --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice, on vLLM 0.21.0 or later
  2. Thinking is off in the template unless you pass enable_thinking true or start the server with --default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding
  3. Pass earlier reasoning back as reasoning_content in the history, since the card says reasoning may stop in later steps if it's dropped
  4. Sampling per the card is temperature 1.0 and top_k 20
  5. The FP8 build's Docker image and serve.sh predate upstream support and set a 4,096-token context, so prefer a released vLLM
  6. It doesn't fit our 128 GB reference machine at any published precision
  7. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented

Questions

Which is better for AI agents, Arete-27B or Laguna M.1?

Laguna M.1 scores 56.7 (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 Laguna M.1

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