LLaDA MoE 7B A1B Instruct is an open-source language model by inclusionAI. Features: 7.4b LLM, VRAM: 14.7GB, Context: 8K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.23.
| LLM Name | LLaDA MoE 7B A1B Instruct |
| Repository 🤗 | https://huggingface.co/inclusionAI/LLaDA-MoE-7B-A1B-Instruct |
| Model Size | 7.4b |
| Required VRAM | 14.7 GB |
| Updated | 2026-10-12 |
| Maintainer | inclusionAI |
| Model Type | llada |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LLaDAMoEModel |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 157184 |
| Torch Data Type | bfloat16 |