LLM Comparison
MiniCPM vs Nemotron 3 Super
Side-by-side specs, pricing & capabilities · Updated September 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 20 | |
| Family | MiniCPM | Nemotron |
| Status | Current | Current |
| Release Date | — | Mar 2026 |
| Context Window | 128K tokens | 262K tokens |
| Input Price | — | — |
| Output Price | — | — |
| Pricing Notes | Open-weight GitHub and Hugging Face model family. There is no fixed vendor API price; runtime cost depends on the host, hardware, or inference provider. | Free tier available on OpenRouter with rate limits |
| Capabilities | textcodereasoninglocal-inference | textcode |
| Training Cutoff | Not publicly specified in queued source | — |
| Max Output | 33K tokens | 262K tokens |
| API Identifier | OpenBMB/MiniCPM | nvidia/nemotron-3-super-120b-a12b:free |
| Benchmarks | ||
| MiniCPM-SALA standard benchmark average | 76.53official-github-readme | — |
| MiniCPM-SALA long-context average | 38.97official-github-readme | — |
| MiniCPM-SALA 2048K extrapolation score | 81.6official-github-readme | — |
| MiniCPM4.1 reasoning decoding speedup | 3official-github-readme | — |
| MiniCPM4 Jetson AGX Orin decoding speedup vs Qwen3-8B | 7official-github-readme | — |
| View MiniCPM | View Nemotron 3 Super | |
OpenBMB
MiniCPM
MiniCPM is OpenBMB’s ultra-efficient open language-model family for edge and end-device deployment. The MiniCPM4 and MiniCPM4.1 lines focus on fast local reasoning, while MiniCPM-SALA extends the family toward sparse/linear attention and million-token context research.
NVIDIA
Nemotron 3 Super
Nemotron 3 Super is a large language model from NVIDIA. Supports up to 262,144 token context window. Available free with rate limits on OpenRouter.
More Comparisons
Looking for more AI models?
Browse All LLMs