Project AURIONAI Use-Cases Research & Innovation
edge LLMfamily

MiniCPM4 / 4.1

OpenBMB on-device model family (MiniCPM4 6 Jun 2025, MiniCPM4.1 5 Sep 2025).

OpenBMB (Tsinghua NLP Lab and ModelBest)
Levelfamily
Classedge LLM
Parametersnot in the notes
Contextnot in the notes
Released6 Jun 2025
Opennessopen weights permissive
Runs onmobile or NPU
Statusactive

Lineage

20252026MiniCPM4 0.5BMiniCPM4 0.5B, Jun 2025MiniCPM4 8B, Jun 2025MiniCPM4.1 8BMiniCPM4.1 8B, Sep 2025

2 members have no release date in the notes, so they are not on this timeline.

OpenBMB (Tsinghua NLP Lab and ModelBest)MiniCPM4.1 8B belongs to this familyedge LLM5 Sep 2025
OpenBMB (Tsinghua NLP Lab and ModelBest)MiniCPM4 0.5B belongs to this familyedge LLM6 Jun 2025
OpenBMB (Tsinghua NLP Lab and ModelBest)MiniCPM4 8B belongs to this familyedge LLM6 Jun 2025
OpenBMB (Tsinghua NLP Lab and ModelBest)BitCPM4 0.5B belongs to this familyedge LLM
OpenBMB (Tsinghua NLP Lab and ModelBest)BitCPM4 1B belongs to this familyedge LLM
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Identity

Developer
OpenBMB (Tsinghua NLP Lab and ModelBest)
Family
not in the notes
Released
6 Jun 2025 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
GPTQ, AWQ, GGUF, MLX variants; over 5x generation acceleration claimed on typical end-side chips (chips not named)
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. huggingface.co/openbmb/MiniCPM4.1-8B-Eagle3/blob/main/README... https://huggingface.co/openbmb/MiniCPM4.1-8B-Eagle3/blob/main/README.md
  2. ai-models/openbmb/MiniCPM4-0.5B , Cloud Native Build cnb.cool https://cnb.cool/ai-models/openbmb/MiniCPM4-0.5B

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MiniCPM4 / 4.1", https://aurion.semai.id/models/openbmb-minicpm4/, records of October 2026.