Model Card on HF 🤗: https://huggingface.co/BlueZeros/MING-MOE-4B
MING MoE 4B 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)
MING MoE 4B Parameters and Internals
| LLM Name | MING MoE 4B |
| Repository 🤗 | https://huggingface.co/BlueZeros/MING-MOE-4B |
| Model Size | 4b |
| Required VRAM | 0.3 GB |
| Updated | 2025-10-17 |
| Maintainer | BlueZeros |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|o_proj|q_proj|k_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to MING MoE 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen 3 4B Text To SQL | 0K / 8.1 GB | 124 | 2 |
| Crystal Think V2 | 0K / 8.1 GB | 5 | 7 |
| Crystal Think V1.0 | 0K / 8.1 GB | 52 | 1 |
| Crystal Think V1 | 0K / 8.1 GB | 52 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than BlueZeros/MING-MOE-4B .
Rank the MING MoE 4B 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? 51629 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124