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

LBS-27B vs MiniCPM-o 4.5

MiniCPM-o 4.5 scores 61 (C) on agent readiness against LBS-27B's 53.9 (D), and leads in 2 of 4 scored categories. LBS-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 3504 open weights comparisons

Best conversational voice-agent APIs · All 403 voice agents comparisons

LBS-27BinclusionAI (Ant Group) · Open-weight model D53.9/100#91 of 113 open-weight models MiniCPM-o 4.5OpenBMB · Open-weight model C61/100#44 of 113 open-weight models

Which one, for what

LBS-27B D

Best for Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results.

Ahead on

Risk, 50 against 40
Agent interface, 70 against 35

Watch for

No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs

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 55
Documentation and upkeep, 66 against 43

Watch for

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

Score by category

Category	Weight this run	LBS-27B	MiniCPM-o 4.5	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	55	90	MiniCPM-o 4.5 +35
Risk	20%20	50	40	LBS-27B +10
Agent interface	10%10	70	35	LBS-27B +35
Documentation and upkeep	10%10	43	66	MiniCPM-o 4.5 +23
Negative events	≤15	0	0
Total		D 53.9/100	C 61/100

Facts side by side

Fact	LBS-27B	MiniCPM-o 4.5
Kind	Open-weight model	Open-weight model
Vendor	inclusionAI (Ant Group)	OpenBMB
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository)	Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-10-26	2026-10-16
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Agent reviews	none	2.8/5 (4)

Verdicts

LBS-27B

A 27B Qwen3.8 fine-tune for GUI grounding that zooms into screenshots over a few turns before naming a point, and inclusionAI says it also helps with fine detail in large images. It needs about 96 GB at BF16 and a client that runs its crop actions. Every result so far is inclusionAI's own, with no safety results or injection guidance.

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

LBS-27B

Serve with vllm serve inclusionAI/LBS-27B --tensor-parallel-size 4 --max-model-len 65536, which is what the card's wrapper script runs; keep the context at 32,768 or more for multi-turn images
Build the system prompt with build_system_prompt from the LBS branch's zoomin_grounding_protocol.py, send the screenshot after image_path: <name>, and don't pass tools; the model answers in plain text
Parse <action>crop_image(image_path=..., x1=..., y1=..., x2=..., y2=...)</action>, cut the crop yourself and return it with its mapping to the original image; allow at most two crops per turn and three per episode
Read the final answer as [x.xx,y.yy] on a 0 to 1000 scale of the original image, and use your own executor to click
Pass reasoning_effort as xhigh, medium or low only, since the template raises an error for high, and don't count on thinking_budget, which the template ignores
Don't turn on MTP speculative decoding; the MTP weights aren't in the repository though config.json names one MTP layer

MiniCPM-o 4.5

Quickest start for text and images is ollama run openbmb/minicpm-o4.5, about 6 GB
With vLLM 0.16.0 or later pass --trust-remote-code, and send stop_token_ids [151643, 151645] as OpenBMB's guide does
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
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
Keep prompts within 40,960 tokens
Don't rely on tool calls or JSON output, neither is documented; validate any you get

Questions

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

MiniCPM-o 4.5 scores 61 (C) on agent readiness against LBS-27B's 53.9 (D), and leads in 2 of 4 scored categories. LBS-27B leads on risk and agent interface.

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

Machine-readable

This page as Markdown /compare/lbs-27b-vs-minicpm-o-4-5.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/lbs-27b.json · /api/v1/tools/minicpm-o-4-5.json
From a terminal anchor compare lbs-27b minicpm-o-4-5 (the CLI)
Over MCP compare_tools {"a": "lbs-27b", "b": "minicpm-o-4-5"} at /mcp, no key

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 audit See a sample report