llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsMiniCPM SALA

OpenBMB model product

MiniCPM SALA

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% Lightning Attention layers, achieving up to 3.5x inference speed over dense baselines at 256K tokens. With HyPE (Hybrid Positional Encoding) and NoPE in sparse layers, the model extrapolates to 2048K tokens despite a 520K training length, enabling 1M-token inference on consumer GPUs like the RTX 5090.

Updated Aug 10, 2026. Default version: MiniCPM-SALA

Compare
LLMBoard scoreN/ANot scored
CoverageN/ANo published score
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
MiniCPM-SALA
Released
Feb 11, 2026
Knowledge cutoff
Unknown
Parameters
9.5B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

No capability profile

No published version under this unique model currently has enough benchmark coverage to calculate a score.

Benchmark results

Published benchmark records for the scored version currently unavailable.

No benchmark rows

No published benchmark result is linked to the scored version.

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

MiniCPM SALA versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

MiniCPM-SALAFeb 11, 2026N/A9.5BN/AN/ANoApache 2.0

What is MiniCPM SALA?

A concise description based on the published model registry.

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% Lightning Attention layers, achieving up to 3.5x inference speed over dense baselines at 256K tokens. With HyPE (Hybrid Positional Encoding) and NoPE in sparse layers, the model extrapolates to 2048K tokens despite a 520K training length, enabling 1M-token inference on consumer GPUs like the RTX 5090.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Models similar to MiniCPM SALA

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#170
AC

Qwen3.5 0.8B

Alibaba Cloud / Qwen Team

0.3 LLMBoard

DetailsCompare
#169
GO

Gemma 3 1B

Google

2.7 LLMBoard

DetailsCompare
#168
GO

Gemma 3n E2B

Google

6.9 LLMBoard

DetailsCompare
#167
AC

Qwen3 VL 4B

Alibaba Cloud / Qwen Team

7.7 LLMBoard

DetailsCompare
#166
BA

ERNIE 4.5

Baidu

8.1 LLMBoard

DetailsCompare
#165
GO

Gemma 3n E2B LiteRT

Google

8.3 LLMBoard

DetailsCompare

FAQ

Common questions about MiniCPM SALA.

When was MiniCPM SALA released?

MiniCPM SALA's default version was released on Feb 11, 2026.

How much does MiniCPM SALA cost?

No official standard PAYG price is currently available for MiniCPM SALA.

Who created MiniCPM SALA?

MiniCPM SALA is published under OpenBMB in the model registry.

What is the context window for MiniCPM SALA?

The current registry does not publish a context window for the default version.

Is MiniCPM SALA open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer MiniCPM SALA?

No published provider offering is currently linked to the default version.

What models should I compare MiniCPM SALA with?

No nearby ranked alternatives are currently available.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai