Model Card on HF 🤗: https://huggingface.co/DataPilot/ArrowNeo-AME-3x4B-v0.1-MoE
ArrowNeo AME 3x4B V0.1 MoE 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)
ArrowNeo AME 3x4B V0.1 MoE Parameters and Internals
| LLM Name | ArrowNeo AME 3x4B V0.1 MoE |
| Repository 🤗 | https://huggingface.co/DataPilot/ArrowNeo-AME-3x4B-v0.1-MoE |
| Base Model(s) | |
| Model Size | 7.8b |
| Required VRAM | 15.6 GB |
| Updated | 2025-09-23 |
| Maintainer | DataPilot |
| Model Type | mixtral |
| Model Files | |
| Supported Languages | ja en |
| Model Architecture | MixtralForCausalLM |
| License | mit |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.50.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives to ArrowNeo AME 3x4B V0.1 MoE
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ArrowNeo AME 4x3B V0.1 MoE | 8K / 15.6 GB | 10 | 6 |
| MoECPM Untrained 4x2b | 2K / 15.7 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than DataPilot/ArrowNeo-AME-3x4B-v0.1-MoE .
Rank the ArrowNeo AME 3x4B V0.1 MoE 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? 51566 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124