Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
nvidia
|
|---|---|
| Company | nvidia |
| Release Date | 2026-05-19 |
| Parameters (B) | 8 |
| Architecture | Block Diffusion Transformer |
| Context Window | 262144 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 18 |
| Compute | Single NVIDIA GPU with 16GB+ VRAM for BF16 inference (recommended 24GB+ with KV cache headroom) |
| Benchmark: ARC | 58.1 |
| Benchmark: GSM8K | 88.2 |
| Benchmark: HellaSwag | 76.1 |
| Benchmark: HumanEval | 60.4 |
| Benchmark: MBPP | 68.2 |
| Benchmark: MMLU | 74.7 |
| Pricing (Input) | — |
| Pricing (Output) | — |