Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM4-8B-marlin-cpmcu
MiniCPM4 8B Marlin Cpmcu 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 8B Marlin Cpmcu Parameters and Internals
| LLM Name | MiniCPM4 8B Marlin Cpmcu |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM4-8B-marlin-cpmcu |
| Merged Model | Yes |
| Model Size | 8b |
| Required VRAM | 5.1 GB |
| Updated | 2025-06-16 |
| Maintainer | openbmb |
| Model Type | minicpm |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | MiniCPMForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 73448 |
| Torch Data Type | float16 |
Best Alternatives to MiniCPM4 8B Marlin Cpmcu
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM4 8B | 32K / 16.4 GB | 7040 | 243 |
| MiniCPM4 8B Eagle VLLM | 32K / 2.3 GB | 1411 | 7 |
| MiniCPM4 8B Marlin VLLM | 32K / 5.2 GB | 403 | 6 |
| MiniCPM4 Survey | 32K / 16.5 GB | 200 | 9 |
| MiniCPM4 8B Eagle FRSpec | 32K / 1.1 GB | 146 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM4-8B-marlin-cpmcu .
Rank the MiniCPM4 8B Marlin Cpmcu 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? 48168 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124