DataLearner logo
MI

MiniCPM-V 4.6

Multimodal modelV 4.6

MiniCPM-V 4.6

Release date: 2026-05-11Updated: 2026-07-17 21:58:05.598870
Live demoGitHubHugging FaceCompare
Parameters
1.3B
Context length
262K
Chinese support
Supported
Reasoning ability

MiniCPM-V 4.6 is a multimodal model from OpenBMB, released on 2026-05-11. It accepts text, image, and video input and returns text output. The cataloged parameter count is 1.3B. The recorded context window is 262K, and the recorded maximum output is 4K. Cataloged capabilities include Multilingual. The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

MiniCPM-V 4.6

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
262K tokens
Max output length
4K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Video → Text
Release date
2026-05-11
Model file size
~1.6GB (Q4_K_M GGUF)
MoE architecture
No
Total params / Active params
1.3B / N/A
Knowledge cutoff
No data
MiniCPM-V 4.6

Open source & experience

MiniCPM-V 4.6

Official resources

Paper
Paper
DataLearnerAI blog
No blog post yet
MiniCPM-V 4.6

API details

API speed
3/5
No public API pricing yet.
MiniCPM-V 4.6

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

MiniCPM-V 4.6

Publisher

MiniCPM-V 4.6

Model Overview

MiniCPM-V 4.6 is a multimodal model from OpenBMB, released on 2026-05-11.

It accepts text, image, and video input and produces text output. Its cataloged capabilities include Multilingual. The cataloged parameter count is 1.3B. The recorded context window is 262K, and the recorded maximum output is 4K.

The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. The page links 4 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

MiniCPM-V 4.6

FAQ

What is MiniCPM-V 4.6?

MiniCPM-V 4.6 is a multimodal model from OpenBMB, released on 2026-05-11. It accepts text, image, and video input and returns text output. The cataloged parameter count is 1.3B. The recorded context window is 262K, and the recorded maximum output is 4K. Cataloged capabilities include Multilingual. The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does MiniCPM-V 4.6 support?

The current model record lists text, image, and video as input and text as output.

What are the main recorded specifications for MiniCPM-V 4.6?

The cataloged parameter count is 1.3B. The recorded context window is 262K, and the recorded maximum output is 4K. Fields without a source-backed value remain undisclosed.

Why is no API price shown for MiniCPM-V 4.6?

Open-weight checkpoint; no first-party hosted price published.

Why are no benchmark results shown for MiniCPM-V 4.6?

No exact-model official score could be mapped safely to the current catalog.

Is MiniCPM-V 4.6 open source?

The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code