MiniCPM4.1 8B is an open-source language model by openbmb. Features: 8b LLM, VRAM: 16.3GB, Context: 64K, License: apache-2.0, LLM Explorer Score: 0.34.
Arxiv:2506.07900 Arxiv:2509.24663 Conversational Custom code En Minicpm Region:us Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM4.1-8B
MiniCPM4.1 8B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MiniCPM4.1 8B Parameters and Internals
| LLM Name | MiniCPM4.1 8B |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM4.1-8B |
| Model Size | 8b |
| Required VRAM | 16.3 GB |
| Updated | 2026-05-28 |
| Maintainer | openbmb |
| Model Type | minicpm |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | MiniCPMForCausalLM |
| License | apache-2.0 |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.56.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 73448 |
| Torch Data Type | bfloat16 |
Best Alternatives to MiniCPM4.1 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM4 8B | 32K / 16.4 GB | 19539 | 283 |
| MiniCPM4 8B Eagle VLLM | 32K / 2.3 GB | 1778 | 10 |
| MiniCPM4 8B Eagle FRSpec | 32K / 0 GB | 721 | 9 |
| MiniCPM4 Survey | 32K / 16.5 GB | 648 | 14 |
| MiniCPM4 8B Marlin Cpmcu | 32K / 5.1 GB | 56 | 8 |
| MiniCPM4 8B Marlin VLLM | 32K / 5.2 GB | 57 | 7 |
Rank the MiniCPM4.1 8B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54059 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a