Model Card on HF 🤗: https://huggingface.co/cloudyu/S1-Llama-3.2-3Bx4-MoE
S1 Llama 3.2 3Bx4 MoE Benchmarks
MMLU Pro: 22.71
GPQA: 5.82
MUSR: 6.17
BBH: 20.04
IFEval: 53.02 vs 88 (so35)-39.8%
MATH Lvl 5: 12.01
LLME Score: 0.25789
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)
S1 Llama 3.2 3Bx4 MoE Parameters and Internals
| LLM Name | S1 Llama 3.2 3Bx4 MoE |
| Repository 🤗 | https://huggingface.co/cloudyu/S1-Llama-3.2-3Bx4-MoE |
| Model Size | 9.6b |
| Required VRAM | 38 GB |
| Updated | 2025-09-20 |
| Maintainer | cloudyu |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | llama3 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|begin_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float32 |
Rank the S1 Llama 3.2 3Bx4 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124