LLaDA2.0 Flash 4bit is an open-source language model by mlx-community. Features: 102.9b LLM, VRAM: 57.8GB, Context: 32K, License: apache-2.0, Quantized.
| LLM Name | LLaDA2.0 Flash 4bit |
| Repository ๐ค | https://huggingface.co/mlx-community/LLaDA2.0-flash-4bit |
| Base Model(s) | |
| Model Size | 102.9b |
| Required VRAM | 57.8 GB |
| Updated | 2026-03-27 |
| Maintainer | mlx-community |
| Model Type | llada2_moe |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LLaDA2MoeModelLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 157184 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LLaDA2.0 Flash Preview 4bit | 16K / 57.8 GB | 90 | 3 |
๐ 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! ๐