Model reference · open weights
LLaDA is an open-weight language model from GSAI-ML. LLaDA-8B-Instruct (BF16) weighs 16.0 GB; the smallest configuration that runs it is RTX 4090 24 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
What it is
| Released by | GSAI-ML |
|---|---|
| Released | 2025-02-19 |
| Parameters | 8.0B |
| VRAM | 16.0 GB for the weights |
What it runs on
How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.
| Card | Weights alone |
|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB 2 smaller cards | does not fit |
| RTX 3090 24 GB | fits |
| RTX 4090 24 GB | fits |
| RTX 5090 32 GB | fits |
| L40S 48 GB | fits |
| A100 80 GB | fits |
| H100 80 GB | fits |
| RTX PRO 6000 Blackwell 96 GB | fits |
| DGX Spark (GB10) 128 GB unified | fits |
| H200 141 GB | fits |
| B200 180 GB | fits |
From the model card
We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.
[2025-10-21] We have modified modeling_llada.py to support the input of attention_mask.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.