Autotrain compatible Base model:3rd-degree-burn/lla... Base model:arliai/llama-3.1-8b... Base model:joseph717171/llama-... Base model:merge:3rd-degree-bu... Base model:merge:arliai/llama-... Base model:merge:joseph717171/... Base model:merge:rombodawg/rom... Base model:rombodawg/rombos re... Codegen Conversational Endpoints compatible Frankenmoe Instruct Merge Mergekit Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/moeru-ai/L3.1-Moe-4x8B-v0.2
L3.1 MoE 4x8B V0.2 Benchmarks
MMLU Pro: 19.58
GPQA: 2.24
MUSR: 2.29
BBH: 21.34
IFEval: 54.07 vs 88 (so35)-38.6%
MATH Lvl 5: 10.35
LLME Score: 0.23796
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)
L3.1 MoE 4x8B V0.2 Parameters and Internals
| LLM Name | L3.1 MoE 4x8B V0.2 |
| Repository 🤗 | https://huggingface.co/moeru-ai/L3.1-Moe-4x8B-v0.2 |
| Base Model(s) | |
| Model Size | 24.9b |
| Required VRAM | 50.1 GB |
| Updated | 2025-09-23 |
| Maintainer | moeru-ai |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | MixtralForCausalLM |
| License | llama3.1 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|begin_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Rank the L3.1 MoE 4x8B V0.2 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124