Elly 768 MoE 4bit is an open-source language model by assassindesign. Features: 31m LLM, VRAM: 0.1GB, Context: 32K, MoE, Quantized, LLM Explorer Score: 0.3.
| LLM Name | Elly 768 MoE 4bit |
| Repository π€ | https://huggingface.co/assassindesign/Elly-768-MoE-4bit |
| Base Model(s) | |
| Model Size | 31m |
| Required VRAM | 0.1 GB |
| Updated | 2026-08-30 |
| Maintainer | assassindesign |
| Model Type | qwen3_moe |
| Model Files | |
| Supported Languages | zh en |
| Quantization Type | 4bit |
| Model Architecture | Qwen3MoeForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 5.8.1 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 6400 |