Sign in

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

Arete-27B vs MiniCPM-o 4.5

MiniCPM-o 4.5 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 agent interface. 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

Best conversational voice-agent APIs · All 546 voice agents comparisons

Arete-27BNous Research · Open-weight model C55.1/100#105 of 135 open-weight models MiniCPM-o 4.5OpenBMB · Open-weight model C61/100#48 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 40
  • Agent interface, 60 against 35

Watch for

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

MiniCPM-o 4.5 C

Best for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence.

Ahead on

  • Reach, 90 against 50

Watch for

Speech output and full duplex need trust_remote_code with Transformers 4.51.0 or OpenBMB's llama.cpp-omni

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 MiniCPM-o 4.5 +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.

MiniCPM-o 4.5 90

Memory 30, OpenBMB's 4-bit GGUF with its vision file is 5.9 GB, about 7 GB with a fifth added. Runtimes 15 of 25, released vLLM, llama.cpp and Ollama run it, while Transformers 5.22.1 still needs OpenBMB's remote code and SGLang 0.5.23 supports only the older 2.6. Builds 15, GGUF at several precisions plus AWQ and GPTQ. Terms 15, plain Apache 2.0. Download 10, nothing gated. Hosted 5, OpenBMB's own API serves it.

Agent interface Arete-27B +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.

MiniCPM-o 4.5 35

Chat template 20, a Jinja template in the tokenizer config. Tool-calling format 10 of 25, only the inherited Qwen3 template says how tools work. Trained tool calling 0, OpenBMB never mentions tool use. Structured output 0, not documented. Reasoning control 0, thinking turns on and off per request but nobody says where the reasoning comes back. Context 5, 40,960 tokens. Read as an omni model, it takes images, video and audio and returns text and streaming speech, which the card documents with code.

Risk Arete-27B +15

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.

MiniCPM-o 4.5 40

File safety 5 of 25, two pickle files sit in the speech stage and the documented load runs repository code. Provenance 15, the files are in the openbmb organisation OpenBMB's GitHub links, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 5, general cautions only, nothing about voice cloning misuse, prompt injection or refusals. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt, policy or advisories.

Score by category

CategoryWeight this runArete-27BMiniCPM-o 4.5Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255090MiniCPM-o 4.5 +40
Risk20%205540Arete-27B +15
Agent interface10%106035Arete-27B +25
Documentation and upkeep10%106366MiniCPM-o 4.5 +3
Negative events≤1500
TotalC 55.1/100C 61/100

Facts side by side

FactArete-27BMiniCPM-o 4.5
KindOpen-weight modelOpen-weight model
VendorNous ResearchOpenBMB
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-10-24
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.

MiniCPM-o 4.5

A small omni cousin that sees, listens and talks back, with full-duplex speech and voice cloning, in about 7 GB at 4-bit through llama.cpp or Ollama for text and images. Speech output needs OpenBMB's remote code or llama.cpp-omni, and 28 GB of GPU for the full demo. The main risks are repository code and pickle files and no safety results.

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

MiniCPM-o 4.5

  1. Quickest start for text and images is ollama run openbmb/minicpm-o4.5, about 6 GB
  2. With vLLM 0.16.0 or later pass --trust-remote-code, and send stop_token_ids [151643, 151645] as OpenBMB's guide does
  3. vLLM, llama.cpp and Ollama return text only; for speech out use the card's Transformers 4.51.0 code or OpenBMB's llama.cpp-omni
  4. In llama.cpp pass both the language GGUF and MiniCPM-o-4_5-vision-F16.gguf with --mmproj, and use --jinja --reasoning-budget 0 to turn thinking off
  5. Keep prompts within 40,960 tokens
  6. Don't rely on tool calls or JSON output, neither is documented; validate any you get

Questions

Which is better for AI agents, Arete-27B or MiniCPM-o 4.5?

MiniCPM-o 4.5 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 agent interface.

Other comparisons with Arete-27B or MiniCPM-o 4.5

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