Base model:finetune:tiiuae/fal... Base model:tiiuae/falcon3-10b-... Frankenmoe Instruct Lazymergekit Merge Mergekit Mixtral Moe Region:us Safetensors Sharded Tensorflow Tiiuae/falcon3-10b-instruct
Model Card on HF 🤗: https://huggingface.co/qingy2024/Falcon3-2x10B-MoE-Instruct
Falcon3 2x10B MoE Instruct Benchmarks
MMLU Pro: 38.04
GPQA: 10.74
MUSR: 12.91
BBH: 45.07
IFEval: 78.5 vs 88 (so35)-10.8%
MATH Lvl 5: 27.95
LLME Score: 0.29951
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)
Falcon3 2x10B MoE Instruct Parameters and Internals
| LLM Name | Falcon3 2x10B MoE Instruct |
| Repository 🤗 | https://huggingface.co/qingy2024/Falcon3-2x10B-MoE-Instruct |
| Base Model(s) | |
| Model Size | 18.8b |
| Required VRAM | 37.6 GB |
| Updated | 2025-05-06 |
| Maintainer | qingy2024 |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Rank the Falcon3 2x10B MoE Instruct 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