Model reference · open weights

MiniCPM-o-4_5

MiniCPM-o-4_5 is an open-weight language model from openbmb, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs openbmb 4 variants 964k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What MiniCPM-o-4_5 is

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone GitHub | CookBook | Omni-modal Demo | Vision-Language Demo </br WeChat | Discord | MiniCPM Wiki(Chinese) | CaseBook(Audio, Omni Full-Duplex) News [!NOTE] [2026.02.06] 🥳 🥳 🥳 We open-sourced a realtime web demo deployable on your own devices like Mac or GPU. Try it now! MiniCPM-o 4.5 MiniCPM-o 4.5 is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include: - 🔥 Leading Visual Capability. MiniCPM-o 4.5 achieves an average score of 77.6 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 9B parameters, it surpasses widely used proprietary models like GPT-4o, Gemini 2.0 Pro, and approaches Gemini 2.5 Flash for vision-language capabilities. It supports instruct and thinking modes in a single model, better covering efficiency and performance trade-offs in different user scenarios. - 🎙 Strong Speech Capability. MiniCPM-o 4.5 supports bilingual real-time speech conversation with configurable voices in English and Chinese. It features more natural, expressive and stable speech conversation. The model also allows for fun features such as voice cloning and role play via a simple reference audio clip, where the cloning performance surpasses strong TTS tools such as CosyVoice2. - 🎬 New Full-Duplex and Proactive Multimodal Live Streaming Capability. As a new feature, MiniCPM-o 4.5 can process real-time, continuous video and audio input streams simultaneously while generating concurrent text and speech output streams in an end-to-end fashion, without mutual blocking. This allows MiniCPM-o 4.5 to see, listen, and speak simultaneously, creating a fluid, real-time omnimodal conversation experience. Beyond reactive responses, the model can also perform proactive interaction, such as initiating reminders or comments based on its continuous understanding of th

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makeropenbmb
TypeLanguage models
Parameters (lead)9.4B
Context40k tokens
Variants4
Runs withtransformers
Released2026-02-03
Popularity964k downloads / month
Likes1,478
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
MiniCPM-o-4_59.4BBF16~21.6 GBWeights ↗
MiniCPM-o-4_5-awq9.4BAWQWeights ↗
MiniCPM-o-4_5-ggufGGUFWeights ↗
MiniCPM-o-4_5-GPTQ9.4BGPTQWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys minicpm-o-4-5 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minicpm-o-4-5 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minicpm-o-4-5","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Tags

transformers onnx safetensors minicpmo feature-extraction minicpm-o minicpm-v multimodal full-duplex any-to-any custom_code 4-bit awq gguf

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want MiniCPM-o-4_5 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms