Compare / MiniCPM-SALA vs Apertus 1.5 8B
MiniCPM-SALA vs Apertus 1.5 8B
Updated November 2026
Verdict
MiniCPM-SALA scores higher on the Small LM Index: 52.6 vs 20.1. On the 1 benchmark both labs report, MiniCPM-SALA wins 1 and Apertus 1.5 8B wins 0. Both need about 7.2 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick MiniCPM-SALA if…
- you want the strongest model overall
- you work with long documents
Pick Apertus 1.5 8B if…
- you need image input
- you want the more widely used model (more quantized builds and community support)
Specifications
| MiniCPM-SALA | Apertus 1.5 8B | |
|---|---|---|
| Small LM Index | 52.6 (likely 48–57) | 20.1 (likely 15–28) |
| Lab | OpenBMB (MiniCPM) · China | Swiss AI Initiative (Apertus) · Europe |
| Released | 2026-02-11 | 2026-07-24 |
| Parameters | 9.5B (dense) | 8.9B (dense) |
| Memory at 4-bit | ~6.7 GB | ~7.2 GB |
| Context window | 1M tokens | 262K tokens |
| Input | text | text, image, audio |
| Reasoning | Hybrid (thinking on/off) | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 3.7K | 42K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | MiniCPM-SALA | Apertus 1.5 8B |
|---|---|---|
| MMLU-Pro Knowledge | 67.0 | 48.8 |
| GPQA Diamond Knowledge | ≈ 66 | 27.2 |
| AIME Math | 78.3 | ≈ 16 |
| LiveCodeBench Coding | 52.0 | ≈ 20 |
| IFEval Instruction following | 76.3 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, MiniCPM-SALA or Apertus 1.5 8B?
MiniCPM-SALA scores higher on the Small LM Index: 52.6 vs 20.1. On the 1 benchmark both labs report, MiniCPM-SALA wins 1 and Apertus 1.5 8B wins 0.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 7.2 GB of memory at 4-bit quantization.
Which has the longer context window?
MiniCPM-SALA has the longer context window: 1M tokens against 262K.
Can I use MiniCPM-SALA and Apertus 1.5 8B commercially?
Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.