AREX Turbo 4bit is an open-source language model by mlx-community. Features: 991.5m LLM, VRAM: 3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.
| LLM Name | AREX Turbo 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/AREX-Turbo-4bit |
| Base Model(s) | |
| Model Size | 991.5m |
| Required VRAM | 3 GB |
| Updated | 2026-08-10 |
| Maintainer | mlx-community |
| Model Type | qwen3_5 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen3_5ForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 5.2.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |