OpenBMBReleased on Feb 11, 2026

MiniCPM-SALA: Benchmarks, Pricing & Size

MiniCPM-SALA is a language model from OpenBMB, released in February 2026.

MiniCPM-SALA (Sparse Attention and Linear Attention) is a 9B hybrid model built from a MiniCPM-4.0 checkpoint via continual training (~2T tokens, 25% of training-from-scratch cost). It interleaves 25% InfLLM-V2 sparse attention and 75%

MiniCPM-SALA model size

MiniCPM-SALA has 9.5 billion parameters. See how it compares to other models in the same parameter range.

Parameters
9.5B
Small (3–10B)
9.5B
1B7B70B405B

MiniCPM-SALA API

API access coming soon

MiniCPM-SALA will be available through our gateway shortly.

MiniCPM-SALA examples

Recent arena outputs from MiniCPM-SALA, picked from the highest-ranked matchups.

MiniCPM-SALA license

MiniCPM-SALA is released under the Apache 2.0 license, which permits commercial use, has 9.5B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
9.5B

Apache License 2.0 - allows commercial use

FAQ

Common questions about MiniCPM-SALA.

When was MiniCPM-SALA released?

MiniCPM-SALA was released on February 11, 2026 by OpenBMB. This is the official MiniCPM-SALA release date tracked on LLM Stats.

How big is MiniCPM-SALA?

MiniCPM-SALA has 9.5 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created MiniCPM-SALA?

MiniCPM-SALA was created by OpenBMB.

What is the license for MiniCPM-SALA?

MiniCPM-SALA is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where is the MiniCPM-SALA paper or technical report?

MiniCPM-SALA has a paper or technical report available at https://github.com/OpenBMB/MiniCPM/blob/main/docs/MiniCPM_SALA.pdf. Use that source for architecture, training, release and evaluation details.