Arxiv:2404.06395 4-bit Conversational Custom code En Gptq Minicpm3 Quantized Region:us Safetensors Zh
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM3-4B-GPTQ-Int4
MiniCPM3 4B GPTQ Int4 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)
MiniCPM3 4B GPTQ Int4 Parameters and Internals
| LLM Name | MiniCPM3 4B GPTQ Int4 |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM3-4B-GPTQ-Int4 |
| Model Size | 4b |
| Required VRAM | 2.4 GB |
| Updated | 2025-09-23 |
| Maintainer | openbmb |
| Model Type | minicpm3 |
| Model Files | |
| Supported Languages | zh en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MiniCPM3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.0 |
| Tokenizer Class | MiniCPMTokenizer |
| Vocabulary Size | 73448 |
| Torch Data Type | float16 |
Best Alternatives to MiniCPM3 4B GPTQ Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM3 4B | 32K / 8.2 GB | 22366 | 417 |
| OpenBNB MiniCPM3 4B | 32K / 8.2 GB | 6 | 0 |
| MiniCPM3 4B GGUF | 32K / 8.2 GB | 31 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM3-4B-GPTQ-Int4 .
Rank the MiniCPM3 4B GPTQ Int4 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124