Skip to content
RankShark

MiniCPM5-2B

text generation model by openbmb, 1,857 likes on Hugging Face.

ModelOpen sourceby openbmbsince 2026
62.0

SharkScore

#10 in Models

Why it scores 62.0

MiniCPM5-2B has a SharkScore of 62.0/100, ranked #10 of 608 in Models (updated 2026-11-19).

Each part compares MiniCPM5-2B with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
33 · 30%
User reviews
no data · 25%
Maintenance
98 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of MiniCPM5-2B

Automated evaluation by RankShark · 19 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

Not enough public evidence for a full review yet (checked 19 Nov 2026). Below are the facts we could check; we try again on the next run.

Pricing

No public prices found on the pages we checked.

Checked 19 Nov 2026

Free plan
Not stated (checked 19 Nov 2026)
Free trial
Not stated (checked 19 Nov 2026)
Trains on customer data
Not stated (checked 19 Nov 2026)
Data retention
Not stated (checked 19 Nov 2026)
Data regions
Not stated (checked 19 Nov 2026)
Data processing agreement
Not stated (checked 19 Nov 2026)
AI models used
MiniCPM5-2B, described as a dense 2B Transformer. · model card
API
Not stated (checked 19 Nov 2026)
SDKs
Not stated (checked 19 Nov 2026)
Webhooks
Not stated (checked 19 Nov 2026)
Platforms
The vendor describes the model as intended for on-device and local deployment. It also lists an MLX/4-bit variant for Apple Silicon. · model card
Security claims
No security certification stated (checked 19 Nov 2026)

What we measured

Package downloads · 30 days
966,265
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to MiniCPM5-2B

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source