LLaDA models
5 LLaDA models from inclusionAI on Hugging Face, from 8.0B to 16.3B parameters, published by inclusionAI in BF16, with a 32K-token context. The smallest official model, LLaDA2.0-mini, needs about 36.3 GB of VRAM at its published precision; the cheapest live fit is RTX A6000 at $0.363/hr.
Pick a size
One row per official LLaDA size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| LLaDA2.0-mini | 16.3B | 36.3 GB | 18.2 GB | 9.1 GB | RTX A6000 | $0.363/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LLaDA2.0-mini | 16.3B | BF16 | 36.3 GB | RTX A6000 | $0.363/hr |
| LLaDA2.1-mini | 16.3B | BF16 | 36.3 GB | RTX A6000 | $0.363/hr |
Fine-tunes and community models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LLaDA-1.5 | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| LLaDA-8B-Base | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| LLaDA-8B-Instruct | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from inclusionAI
- Ling (3 models)
- inclusionAI (2 models)