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

Inkling vs MiniCPM-o 4.5

Inkling scores 64.2 (B) on agent readiness against MiniCPM-o 4.5's 61 (C), and leads in 3 of 4 scored categories. MiniCPM-o 4.5 leads on reach. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons

Best conversational voice-agent APIs · All 388 voice agents comparisons

InklingThinking Machines Lab · Open-weight model B64.2/100#20 of 100 open-weight models MiniCPM-o 4.5OpenBMB · Open-weight model C61/100#42 of 100 open-weight models

Which one, for what

Inkling B

Best for Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.

Ahead on

Risk, 70 against 40
Agent interface, 85 against 35
Documentation and upkeep, 82 against 66

Watch for

The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation

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

Score by category

Category	Weight this run	Inkling	MiniCPM-o 4.5	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	50	90	MiniCPM-o 4.5 +40
Risk	20%20	70	40	Inkling +30
Agent interface	10%10	85	35	Inkling +50
Documentation and upkeep	10%10	82	66	Inkling +16
Negative events	≤15	0	0
Total		B 64.2/100	C 61/100

Facts side by side

Fact	Inkling	MiniCPM-o 4.5
Kind	Open-weight model	Open-weight model
Vendor	Thinking Machines Lab	OpenBMB
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0	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	2026-07-23	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	3/5 (4)	2.8/5 (4)

Verdicts

Inkling

Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.

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

Inkling

Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it
On 8 B200 GPUs, SGLang's recipe is sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling
Use the inkling tool parser, not Hermes, and the inkling reasoning parser
Pass reasoning_effort as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh
Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card
Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

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, Inkling or MiniCPM-o 4.5?

Inkling scores 64.2 (B) on agent readiness against MiniCPM-o 4.5's 61 (C), and leads in 3 of 4 scored categories. MiniCPM-o 4.5 leads on reach.

Other comparisons with Inkling or MiniCPM-o 4.5

Machine-readable

This page as Markdown /compare/inkling-vs-minicpm-o-4-5.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/inkling.json · /api/v1/tools/minicpm-o-4-5.json
From a terminal anchor compare inkling minicpm-o-4-5 (the CLI)
Over MCP compare_tools {"a": "inkling", "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