MiniCPM-o 4.5

Name: MiniCPM-o 4.5
Author: OpenBMB

OpenBMBOpen WeightsPending Human Review

MiniCPM-o 4.5 is OpenBMB’s end-to-end 9B multimodal conversation model, combining Qwen3-8B, SigLIP2, Whisper-medium, and CosyVoice2 components. It processes text, images, continuous video, and audio while generating concurrent text and speech. Full-duplex streaming supports speaking while listening and proactive responses to a live scene. Thinking and instruction modes balance reasoning with responsiveness. Apache-licensed weights and local demo code were released February 3, before the later technical report and hosted API. It qualifies as a language-capable multimodal model, including substantial visual and spoken question answering rather than transcription or synthesis alone.

2026-02-03

End-to-end full-duplex multimodal language model

Apache-2.0

Compare with other models

Specifications

Parameters: 9B
Architecture: End-to-end full-duplex multimodal language model
License: Apache-2.0
Type: multimodal
Modalities: textimagevideoaudio

Benchmark Scores

Advanced Specifications

Model Family: MiniCPM
Finetuned From: Qwen3-8B
API Access: Available
Chat Interface: Available
Variants: MiniCPM-o-4.5GGUF

Capabilities & Limitations

Capabilities: multimodal conversationfull-duplex speechvisual question answeringvideo understandingreasoning
Known Limitations: Streaming latency depends on hardware and runtime configurationSpeech and visual interpretations can be inaccurateProactive outputs require application-level control over when to respond
Notable Use Cases: local spoken assistantslive visual conversationmultimodal interaction research

Resources

Related Models

MiniCPM-V 4.7 35B-A3B

OpenBMB

MiniCPM-V 4.7 35B-A3B is a public OpenBMB vision-language checkpoint uploaded on October 6. Its official repository contains 16 downloadable BF16 weight shards totaling approximately 35.21B parameters, a hybrid linear/full-attention mixture-of-experts language configuration, and image/video processing metadata. The configuration permits 262,144 positions, but no model card or validated context specification was published in the inspected repository, so no supported context limit is asserted here. Text and visual inputs produce language output through the conditional-generation architecture. The license, training ancestry, evaluated capabilities, and benchmark results remain undisclosed at the audit time; a public weight upload does not supply missing usage rights.

Typemultimodal

Parameters35.21B total; approximately 3B active tier

2026-10-06

Open Weights

Details Compare

MathForm-8B

OpenBMB

MathForm-8B is OpenBMB’s language-to-code model for translating natural-language mathematical statements into Lean 4. It fine-tunes Qwen3-8B on FormalVerse with supervised learning followed by reinforcement learning using compilation and semantic-consistency feedback. The research framework retrieves Mathlib definitions and revises generated formalizations using diagnostics, supporting more faithful mathematical translation. Apache-licensed weights, approximately 367K verified examples, and evaluation code accompany the August 14 paper. This is a named mathematical language specialization; the model is distinct from the surrounding retrieval and verification pipeline. Successful compilation alone does not establish that a formal statement preserves the intended proposition.

UltraX

OpenBMB

UltraX is OpenBMB’s specialized 0.6B language-model release for refining pre-training text through structured editing function calls. It generates insertions, deletions, and replacements rather than rewriting an entire document, and a deterministic executor applies validated edits. Full-parameter supervised training uses program supervision built from language-model refinements and alignment procedures. The July 9 paper precedes the July 13 public code-and-model announcement. Apache-licensed refinement checkpoints and data are available, with no-instruction and preservation-weighted variants grouped here. Its named language-editing specialization qualifies separately from generic data tools or probability-only classifiers.